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

    Neuronpedia

    INDEX
    Explanations

    French

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PRINTF
    -0.07
     답변
    -0.07
     ARR
    -0.06
     debates
    -0.06
    estr
    -0.06
    ób
    -0.06
    اضی
    -0.06
     سف
    -0.06
     strom
    -0.06
    орту
    -0.06
    POSITIVE LOGITS
    ouncing
    0.07
    ti
    0.07
     مشهد
    0.07
    venth
    0.07
    rtype
    0.06
    SKU
    0.06
     butterknife
    0.06
    聲
    0.06
    SHOT
    0.06
    ymous
    0.06
    Act Density 0.056%

    No Known Activations