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

    Neuronpedia

    INDEX
    Explanations

    Physical things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    鼠
    -0.07
    hoc
    -0.07
    ,list
    -0.07
     Static
    -0.06
    widget
    -0.06
    [a
    -0.06
     callBack
    -0.06
    ‌کن
    -0.06
     cheat
    -0.06
    Portfolio
    -0.06
    POSITIVE LOGITS
    ař
    0.06
    .mj
    0.06
    acija
    0.06
    .Screen
    0.06
    _edit
    0.06
     blackjack
    0.06
    337
    0.06
    825
    0.06
    栏
    0.06
    _health
    0.06
    Act Density 0.075%

    No Known Activations