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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    쯤
    -0.07
     /\.
    -0.07
    mai
    -0.06
    Todos
    -0.06
    跳出
    -0.06
    /kubernetes
    -0.06
    젋
    -0.06
    刹
    -0.06
     קישורים
    -0.06
     ">↵
    -0.06
    POSITIVE LOGITS
    andal
    0.07
    Dismiss
    0.07
    isser
    0.07
     nhiễ
    0.07
    CHEDULE
    0.07
    aviors
    0.06
    CRY
    0.06
    (bl
    0.06
    批评
    0.06
    Variables
    0.06
    Act Density 0.090%

    No Known Activations