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

    Neuronpedia

    INDEX
    Explanations

    News and reports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _BUTTON
    -0.07
     Mant
    -0.07
     violating
    -0.07
     יוצא
    -0.07
    _ul
    -0.07
     EI
    -0.07
     fou
    -0.06
     hann
    -0.06
     selections
    -0.06
    נוס
    -0.06
    POSITIVE LOGITS
    conom
    0.07
    鋆
    0.07
    ভ
    0.07
    .where
    0.06
     comments
    0.06
    阍
    0.06
    细菌
    0.06
    ؟
    0.06
    依靠
    0.06
    ye
    0.06
    Act Density 0.054%

    No Known Activations