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

    Neuronpedia

    INDEX
    Explanations

    wired

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ной
    -0.07
    ней
    -0.07
    ichever
    -0.07
    脫
    -0.07
    不堪
    -0.07
     abandoned
    -0.07
    눱
    -0.06
     indexOf
    -0.06
    ansa
    -0.06
    ButtonText
    -0.06
    POSITIVE LOGITS
    调料
    0.08
    -area
    0.08
    ACES
    0.07
    _soup
    0.07
     methodologies
    0.07
    _Location
    0.07
    公报
    0.07
    𝙯
    0.06
    (im
    0.06
    中央空调
    0.06
    Act Density 0.005%

    No Known Activations