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

    Neuronpedia

    INDEX
    Explanations

    Russian language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	full
    -0.06
     Raised
    -0.06
    ifact
    -0.06
    имость
    -0.06
    еві
    -0.06
    コン
    -0.06
    _ADAPTER
    -0.06
     Universidad
    -0.06
    ケット
    -0.06
    �合
    -0.06
    POSITIVE LOGITS
    uluk
    0.07
     بد
    0.06
    say
    0.06
     Flam
    0.06
    Samples
    0.06
    .mousePosition
    0.06
    aoke
    0.06
    ...,
    0.06
     /*!↵
    0.06
    prod
    0.06
    Act Density 0.009%

    No Known Activations