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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pare
    -0.07
    blind
    -0.06
     histoire
    -0.06
     اجرا
    -0.06
     sce
    -0.06
    -paying
    -0.06
    يمي
    -0.06
    füh
    -0.06
     blind
    -0.06
    cratch
    -0.06
    POSITIVE LOGITS
     groin
    0.17
    veriş
    0.08
    .toHexString
    0.08
    ازات
    0.08
     config
    0.07
     intermediary
    0.07
     loin
    0.06
     modifier
    0.06
    Syntax
    0.06
    ập
    0.06
    Act Density 0.003%

    No Known Activations