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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bên
    -0.07
     pocit
    -0.07
     zdroj
    -0.07
     billeder
    -0.06
    ,),↵
    -0.06
    ابق
    -0.06
    院
    -0.06
    Об
    -0.06
    imei
    -0.06
    ěst
    -0.06
    POSITIVE LOGITS
     Femme
    0.07
    stacle
    0.07
     кг
    0.06
    �始化
    0.06
    SectionsIn
    0.06
     Jaguar
    0.06
    .hours
    0.06
    ＿＿＿
    0.06
     euros
    0.06
     outs
    0.06
    Act Density 0.000%

    No Known Activations