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

    Neuronpedia

    INDEX
    Explanations

    Dash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DOMAIN
    -0.07
    енням
    -0.07
    ilor
    -0.07
    маг
    -0.07
     daemon
    -0.06
    ثار
    -0.06
    iliar
    -0.06
    elm
    -0.06
    icari
    -0.06
    popup
    -0.06
    POSITIVE LOGITS
    coal
    0.07
    ré
    0.07
     Kaynak
    0.06
     toplantı
    0.06
     zinc
    0.06
     offsetof
    0.06
     employment
    0.06
    ूब
    0.06
     discretionary
    0.06
     кри
    0.06
    Act Density 0.008%

    No Known Activations