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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    韧
    -0.07
    "${
    -0.07
     بأن
    -0.07
     withdraw
    -0.07
    参与到
    -0.07
    خرج
    -0.06
    集中
    -0.06
    [right
    -0.06
     Laugh
    -0.06
     Eğitim
    -0.06
    POSITIVE LOGITS
    行业协会
    0.08
    loy
    0.07
    裁
    0.07
     DEVICE
    0.07
    .setOutput
    0.07
     oscillator
    0.07
     partnership
    0.07
    _cipher
    0.07
    抡
    0.07
     microphone
    0.07
    Act Density 0.055%

    No Known Activations