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

    Neuronpedia

    INDEX
    Explanations

    detailed references to legal or contractual terms and their implications

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

    Text after certain punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    "correlated", "Emperor", "jour", "depression", "present"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GIVEREF
    -0.55
     Monfieur
    -0.54
    ſelf
    -0.53
    SharedCtor
    -0.53
     protoimpl
    -0.51
     للمعارف
    -0.50
     externi
    -0.49
    IsMutable
    -0.49
    oredCriteria
    -0.48
    ніципалі
    -0.48
    POSITIVE LOGITS
    ">//
    0.48
     Italijanski
    0.45
    ngdoc
    0.41
     poire
    0.40
    ‪
    0.38
    0.36
    onPage
    0.36
    Raw
    0.35
    raw
    0.34
     SDLK
    0.34
    Act Density 1.110%

    No Known Activations