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

    Neuronpedia

    INDEX
    Explanations

    occurrences of double underscore (__) notation commonly used for special methods or attributes in programming languages, particularly in object-oriented programming

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

    constructor or class name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AISSEE
    -0.69
    AndEndTag
    -0.68
    IsMutable
    -0.67
    oneofs
    -0.66
     <>",
    -0.66
    abetes
    -0.65
    uxxxx
    -0.65
     nahilalakip
    -0.65
    ⓧ
    -0.64
    astéroïdes
    -0.63
    POSITIVE LOGITS
    componentWill
    0.36
     process
    0.34
     desmotiv
    0.33
    componentDid
    0.31
     eléctrico
    0.31
     falar
    0.31
     processus
    0.30
     antidesliz
    0.30
    PostConstruct
    0.29
     debes
    0.28
    Act Density 0.001%

    No Known Activations