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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     пищ
    -0.06
    ульт
    -0.06
     mouths
    -0.06
    (te
    -0.06
     پوست
    -0.06
    _VIRTUAL
    -0.06
     comforting
    -0.06
    forcing
    -0.06
    asia
    -0.05
     Disability
    -0.05
    POSITIVE LOGITS
     Pier
    0.07
    <Application
    0.07
     dönemde
    0.07
     aprove
    0.07
     trabaj
    0.06
     whose
    0.06
    ırken
    0.06
     sí
    0.06
     đốc
    0.06
     nebo
    0.06
    Act Density 0.003%

    No Known Activations