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

    Neuronpedia

    INDEX
    Explanations

    conduct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xuất
    -0.08
    市级
    -0.07
     Poll
    -0.07
    坪
    -0.07
    男性
    -0.07
     mej
    -0.07
    アメリカ
    -0.07
    iffies
    -0.06
    Ren
    -0.06
    ائل
    -0.06
    POSITIVE LOGITS
    uckland
    0.07
     thermostat
    0.06
    ++){
↵
    0.06
    _RADIUS
    0.06
    _CTRL
    0.06
    GameOver
    0.06
    generator
    0.06
    続きを
    0.06
    anske
    0.06
    ()){↵
    0.06
    Act Density 0.002%

    No Known Activations