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

    Neuronpedia

    INDEX
    Explanations

    numbers and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    1.16
     is
    1.11
     will
    1.11
     has
    1.03
     was
    1.02
     would
    0.92
     Syndrome
    0.91
     are
    0.90
    );
    0.89
    檛
    0.87
    POSITIVE LOGITS
    i
    1.28
     eerste
    1.11
    𝟯
    1.11
    hitva
    1.10
     erste
    1.08
    ﻴ
    1.08
    РИ
    1.07
     tercera
    1.07
     tripartite
    1.04
     diez
    1.02
    Act Density 0.438%

    No Known Activations