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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    התנהג
    -0.08
    桹
    -0.07
    杓
    -0.07
     pornos
    -0.07
     thủ
    -0.07
    ﴩ
    -0.07
    .logo
    -0.07
     transf
    -0.07
     expression
    -0.07
    罶
    -0.06
    POSITIVE LOGITS
    索赔
    0.07
    jab
    0.06
    加息
    0.06
    xCA
    0.06
    様々な
    0.06
     Dental
    0.06
    wegian
    0.06
    حماية
    0.06
    *a
    0.06
     abandonment
    0.06
    Act Density 0.002%

    No Known Activations