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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hug
    -0.06
    !--
    -0.06
    レット
    -0.06
    ides
    -0.06
     merk
    -0.06
    ھ
    -0.06
    mouth
    -0.06
     кварти
    -0.06
    잔
    -0.06
    .head
    -0.06
    POSITIVE LOGITS
    Upgrade
    0.07
    _FN
    0.07
     Upgrade
    0.06
    (source
    0.06
     actionPerformed
    0.06
     업데이트
    0.06
    restrict
    0.06
     gain
    0.06
     TW
    0.06
     descriptor
    0.06
    Act Density 0.026%

    No Known Activations