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

    Neuronpedia

    INDEX
    Explanations

    minified javascript or css

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     The
    -1.52
    に行く
    -1.52
     “
    -1.48
     it
    -1.47
     about
    -1.44
     into
    -1.44
     tienen
    -1.43
     with
    -1.43
     a
    -1.41
     It
    -1.41
    POSITIVE LOGITS
     作り方
    1.75
     goû
    1.55
    <bos>
    1.53
     coloriage
    1.51
    Prijs
    1.49
    最近は
    1.45
    Nasc
    1.41
    دانلود
    1.40
     kemer
    1.39
    Interes
    1.38
    Act Density 0.002%

    No Known Activations