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

    Neuronpedia

    INDEX
    Explanations

    numbered lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    忍
    -0.08
    iep
    -0.08
     buffering
    -0.08
    Rad
    -0.08
    怀
    -0.08
     dramatic
    -0.07
    脸
    -0.07
    绑
    -0.07
     commercially
    -0.07
    _rad
    -0.07
    POSITIVE LOGITS
     تعريف
    0.09
     bullet
    0.09
     പട്ട
    0.08
     structured
    0.08
     أخبار
    0.08
    ämä
    0.08
     seznam
    0.08
     Tabelle
    0.08
     خطة
    0.08
     Structured
    0.08
    Act Density 0.032%

    No Known Activations