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

    Neuronpedia

    INDEX
    Explanations

    sore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lund
    -0.07
    .printStackTrace
    -0.07
    bia
    -0.07
     강남
    -0.07
     ambitious
    -0.07
    _AMD
    -0.06
     mnist
    -0.06
    itelist
    -0.06
    یان
    -0.06
     بيانات
    -0.06
    POSITIVE LOGITS
     sore
    0.08
    /fire
    0.07
    licensed
    0.07
     sæ
    0.07
     ache
    0.07
     mož
    0.06
     haha
    0.06
     sher
    0.06
     acne
    0.06
    KER
    0.06
    Act Density 0.004%

    No Known Activations