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

    Neuronpedia

    INDEX
    Explanations

    references to food items and their characteristics

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

    circumlocutions and specific object names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bardier
    -0.63
     ब्रेकडाउन
    -0.57
     "..\..\
    -0.53
    EDEFAULT
    -0.50
     IMA
    -0.47
     sometimes
    -0.47
    sometimes
    -0.47
    erover
    -0.46
     REA
    -0.44
     JAS
    -0.44
    POSITIVE LOGITS
     présidenti
    0.47
    MENAFN
    0.47
     menyes
    0.45
    ñata
    0.41
     religieuses
    0.40
     Tér
    0.39
    batik
    0.38
    oredCriteria
    0.38
    calça
    0.37
    uertos
    0.37
    Act Density 0.029%

    No Known Activations