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

    Neuronpedia

    INDEX
    Explanations

    awards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     expectancy
    -0.07
    istol
    -0.06
     Billion
    -0.06
     میلادی
    -0.06
     Gear
    -0.06
     karış
    -0.06
     práva
    -0.06
    descricao
    -0.06
    _revision
    -0.06
     conf
    -0.06
    POSITIVE LOGITS
     uden
    0.07
    sembly
    0.07
    _ep
    0.07
    UILTIN
    0.06
     Liter
    0.06
    —or
    0.06
     enum
    0.06
     ('\
    0.06
    稍
    0.06
    Το
    0.06
    Act Density 0.010%

    No Known Activations