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

    Neuronpedia

    INDEX
    Explanations

    probability calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Skinny
    -0.07
     tore
    -0.07
     transformative
    -0.07
     evapor
    -0.06
     poured
    -0.06
    .".
    -0.06
     century
    -0.06
    advisor
    -0.06
     Democrat
    -0.06
     geo
    -0.06
    POSITIVE LOGITS
     cận
    0.07
    (Target
    0.06
    Hier
    0.06
    CppGuid
    0.06
    较
    0.06
     therefore
    0.06
    รอบ
    0.06
    _PERCENT
    0.06
     beforehand
    0.06
     справа
    0.06
    Act Density 0.003%

    No Known Activations