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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and places

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

    specific names and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dress
    -0.63
    gong
    -0.59
    dır
    -0.57
    dairy
    -0.55
     Normdatei
    -0.54
    groups
    -0.52
    tattoo
    -0.51
    tó
    -0.51
    ground
    -0.50
    trivial
    -0.50
    POSITIVE LOGITS
    ning
    0.71
    nnnn
    0.68
    NNNN
    0.64
    nnn
    0.63
    n
    0.61
    ned
    0.61
    nen
    0.60
    ization
    0.56
    na
    0.52
    ner
    0.51
    Act Density 1.706%

    No Known Activations