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

    Neuronpedia

    INDEX
    Explanations

    code, integers, counting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _dict
    -0.07
    至
    -0.07
    _more
    -0.07
    Match
    -0.06
    ongsTo
    -0.06
    Token
    -0.06
    _FOREACH
    -0.06
    �택
    -0.06
    -buy
    -0.06
    .posts
    -0.06
    POSITIVE LOGITS
    )”
    0.06
     Міністер
    0.06
    ugg
    0.06
     düzenli
    0.06
     darken
    0.06
    jav
    0.06
    LN
    0.06
    _TRANSL
    0.06
     añ
    0.06
     Ce
    0.06
    Act Density 0.038%

    No Known Activations