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

    Neuronpedia

    INDEX
    Explanations

    specific topics and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    0.45
    ख
    0.42
    rne
    0.41
    मान
    0.40
    /
    0.40
    ग
    0.40
    ﺎ
    0.40
    bass
    0.39
    dropBtn
    0.39
     וש
    0.39
    POSITIVE LOGITS
     Codex
    0.48
     nutritive
    0.47
     anthropological
    0.47
     geometrical
    0.46
     crystallography
    0.45
     degenerative
    0.45
     phyt
    0.45
     debat
    0.45
     JMJD
    0.44
     dyslex
    0.44
    Act Density 0.002%

    No Known Activations