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

    Neuronpedia

    INDEX
    Explanations

    static

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ARY
    -0.07
     дерев
    -0.06
     thủy
    -0.06
    MN
    -0.06
    üzel
    -0.06
     Kel
    -0.06
    otent
    -0.06
    oty
    -0.06
    ุข
    -0.06
    _YES
    -0.06
    POSITIVE LOGITS
     static
    0.09
     Anim
    0.07
    stup
    0.06
    数量
    0.06
     defaultValue
    0.06
    λογή
    0.05
     horm
    0.05
    ={({
    0.05
     правиль
    0.05
    tığ
    0.05
    Act Density 0.001%

    No Known Activations