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

    Neuronpedia

    INDEX
    Explanations

    punctuation/stopwords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Titan
    -0.06
     orta
    -0.06
     interruptions
    -0.06
     یوتی
    -0.06
    _FUN
    -0.06
    getMock
    -0.06
     mana
    -0.06
    VectorXd
    -0.06
    onClick
    -0.06
    Fresh
    -0.06
    POSITIVE LOGITS
     прекрас
    0.07
     exacerb
    0.07
     отказ
    0.06
    abei
    0.06
    _KEYWORD
    0.06
    _const
    0.06
    ổng
    0.06
     ویژ
    0.06
    _DL
    0.06
     demonstr
    0.06
    Act Density 0.036%

    No Known Activations