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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific names associated with locations and entities

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

    names and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PCBs
    -0.48
    wantErr
    -0.46
     Constantin
    -0.43
     Kä
    -0.43
    entrySet
    -0.42
     Ooster
    -0.41
    crans
    -0.41
    isDead
    -0.41
    Portail
    -0.41
     Montal
    -0.41
    POSITIVE LOGITS
     Gail
    0.97
    Gail
    0.90
    Bray
    0.87
     Bray
    0.86
     Lob
    0.84
    Gregg
    0.80
    Lob
    0.75
     Gregg
    0.74
     SSE
    0.73
     Chong
    0.69
    Act Density 0.010%

    No Known Activations