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

    Neuronpedia

    INDEX
    Explanations

    punctuation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     আমাদের
    0.61
    Novel
    0.60
     Jeżeli
    0.60
    Jeśli
    0.59
    Thank
    0.59
     Thời
    0.58
    Reference
    0.58
    Our
    0.58
    Ș
    0.58
    Pentru
    0.58
    POSITIVE LOGITS
    ,
    0.44
    ́
    0.42
     unders
    0.41
    os
    0.40
     glyph
    0.38
     soul
    0.38
     –
    0.37
     de
    0.37
     raster
    0.36
     rund
    0.36
    Act Density 0.695%

    No Known Activations