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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ché
    -0.07
    �
    -0.07
    .sig
    -0.07
    긔
    -0.07
    fig
    -0.07
    ağa
    -0.06
     volatility
    -0.06
     obs
    -0.06
     Hours
    -0.06
    leşik
    -0.06
    POSITIVE LOGITS
    литель
    0.07
    ктів
    0.06
     bağır
    0.06
    opl
    0.06
     REST
    0.06
     rost
    0.06
    MER
    0.06
    istol
    0.06
    porto
    0.06
    но
    0.06
    Act Density 0.005%

    No Known Activations