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
     Δι
    -0.07
     Фор
    -0.06
    الأ
    -0.06
    Der
    -0.06
     dalam
    -0.05
    _Header
    -0.05
    شنامه
    -0.05
     Asian
    -0.05
    इस
    -0.05
    “For
    -0.05
    POSITIVE LOGITS
    (mail
    0.07
     konus
    0.07
    tring
    0.07
     наст
    0.07
     ','.
    0.06
    reads
    0.06
    .console
    0.06
     boiled
    0.06
    (Thread
    0.06
    /mol
    0.06
    Act Density 0.013%

    No Known Activations