Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    requests or phrases indicating the need for details and explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    briefly stated

    np_acts-logits-general · gemini-2.5-flash-lite

    It detects section headings and list/numbered-item markers (numbers and words that start list or instruction lines).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.66
    principalColumn
    -0.61
    Tikang
    -0.60
     للمعارف
    -0.52
    -------
    -0.52
     createSlice
    -0.47
    DEPORTES
    -0.47
     CanadaChoose
    -0.46
     sanitaires
    -0.46
     defStyleAttr
    -0.46
    POSITIVE LOGITS
    zul
    0.43
     cour
    0.42
    Around
    0.39
    celo
    0.39
     jum
    0.39
    apun
    0.39
    高原
    0.38
    Apre
    0.38
    Au
    0.38
     aver
    0.38
    Act Density 0.264%

    No Known Activations