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

    Neuronpedia

    INDEX
    Explanations

    URLs or web links

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

    Before ".com"

    np_acts-logits-general · gemini-2.0-flash

    .com URLs and code packages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "..\..\
    -1.03
    Hauptartikel
    -0.87
     ProtoMessage
    -0.84
     unknownFields
    -0.80
     ͡
    -0.79
     "..\..\..\
    -0.76
     متعلقه
    -0.74
    GraphicsUnit
    -0.74
    IsMutable
    -0.73
    expandindo
    -0.73
    POSITIVE LOGITS
    com
    1.11
    COM
    1.05
    Com
    1.00
     COM
    0.91
     Com
    0.90
     com
    0.78
    coms
    0.70
     COMM
    0.67
     KOM
    0.64
     Tome
    0.63
    Act Density 0.035%

    No Known Activations