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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Editing
    -0.07
    ponential
    -0.07
     Gospel
    -0.06
     editing
    -0.06
    Members
    -0.06
    DOMContentLoaded
    -0.06
     falling
    -0.06
     saw
    -0.06
     attacked
    -0.06
     κου
    -0.06
    POSITIVE LOGITS
    ÜM
    0.06
     모두
    0.06
    maktadır
    0.06
     Προ
    0.06
    ž
    0.06
    <Class
    0.06
    _nm
    0.06
    )?
    0.06
    ีม
    0.06
     있다
    0.06
    Act Density 0.001%

    No Known Activations