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

    Neuronpedia

    INDEX
    Explanations

    statistical reporting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DropDown
    -0.07
    otoxic
    -0.07
     Chinese
    -0.06
     Seventh
    -0.06
    QWidget
    -0.06
     habitual
    -0.06
     hourly
    -0.06
     gaussian
    -0.06
     Кроме
    -0.06
    érieur
    -0.06
    POSITIVE LOGITS
     bilm
    0.06
    _subs
    0.06
     Gins
    0.06
     bild
    0.06
     kel
    0.06
     subway
    0.06
    Hang
    0.06
    PLETED
    0.06
     perv
    0.06
    izm
    0.06
    Act Density 0.074%

    No Known Activations