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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .),
    -0.08
     spirituality
    -0.07
     irre
    -0.07
     Anxiety
    -0.07
     Analyzer
    -0.07
     bipolar
    -0.07
    应力
    -0.07
     Football
    -0.07
    肩
    -0.06
     deja
    -0.06
    POSITIVE LOGITS
    甲方
    0.08
    هب
    0.08
    荁
    0.08
    �
    0.07
    ﹸ
    0.07
     הולד
    0.07
    0.07
    .AbsoluteConstraints
    0.07
     second
    0.07
    _bt
    0.07
    Act Density 0.064%

    No Known Activations