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

    Neuronpedia

    INDEX
    Explanations

    stdlib.h in C code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ahami
    1.42
    it
    1.41
    ar
    1.36
     Recognizing
    1.24
     भर्तियों
    1.24
     Feels
    1.24
    am
    1.23
     Doesn
    1.22
    是不
    1.18
     waarop
    1.16
    POSITIVE LOGITS
    נ
    1.51
    AN
    1.20
    ال
    1.14
    פ
    1.09
    ర
    1.08
    п
    1.05
    ר
    1.05
    我对
    1.03
    મ
    1.02
    만
    0.95
    Act Density 0.001%

    No Known Activations