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

    Neuronpedia

    INDEX
    Explanations

    Math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    创建
    -0.07
    -0.06
    پی
    -0.06
     ر
    -0.06
    эй
    -0.06
     Sharia
    -0.06
    	attack
    -0.06
    uracion
    -0.06
     Kültür
    -0.06
     Duterte
    -0.06
    POSITIVE LOGITS
    .de
    0.06
     exceptionally
    0.06
    unding
    0.06
    esses
    0.06
     excluding
    0.06
     most
    0.06
    aload
    0.06
    Most
    0.06
    取消
    0.06
    íd
    0.06
    Act Density 0.036%

    No Known Activations