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

    Neuronpedia

    INDEX
    Explanations

    abortion, health, life-threatening

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الشعر
    -0.08
    油价
    -0.07
     düşük
    -0.07
     appellant
    -0.07
    _name
    -0.07
    メッ
    -0.07
    ulfilled
    -0.07
     сегодня
    -0.07
    aurants
    -0.07
    ellation
    -0.07
    POSITIVE LOGITS
    LOSS
    0.07
    avanaugh
    0.06
     parenthesis
    0.06
    知道
    0.06
    ANGLE
    0.06
    淫
    0.06
    𝒈
    0.06
     Mattis
    0.06
    致使
    0.06
    萎缩
    0.06
    Act Density 0.038%

    No Known Activations