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

    Neuronpedia

    INDEX
    Explanations

    NEGLIGENCE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .session
    -0.07
    كيب
    -0.07
    اطعة
    -0.06
    adero
    -0.06
     USS
    -0.06
     Estados
    -0.06
    LOOR
    -0.06
    aptcha
    -0.06
     gösterir
    -0.06
    라도
    -0.06
    POSITIVE LOGITS
    filtered
    0.07
     niece
    0.07
     Zig
    0.07
    International
    0.07
    _Game
    0.07
     Louisville
    0.07
     ми
    0.06
     negligent
    0.06
     cap
    0.06
     못
    0.06
    Act Density 0.000%

    No Known Activations