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

    Neuronpedia

    INDEX
    Explanations

    software plugins/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    navbarDropdown
    -0.07
    跑道
    -0.07
     fourn
    -0.07
    (rowIndex
    -0.06
    ורג
    -0.06
    .,
    -0.06
     �
    -0.06
     ра�
    -0.06
     OutlineInputBorder
    -0.06
    River
    -0.06
    POSITIVE LOGITS
    _ip
    0.07
    חיפוש
    0.07
    ぜひ
    0.07
     Cluster
    0.07
     episode
    0.07
    -inspired
    0.07
    zos
    0.07
     What
    0.06
     علاقة
    0.06
     cyclic
    0.06
    Act Density 0.131%

    No Known Activations