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

    Neuronpedia

    INDEX
    Explanations

    list items or numbered options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2.11
    ς
    1.50
    s
    1.23
    Н
    1.20
    심히
    1.16
    ählt
    1.16
     this
    1.14
    К
    1.13
    C
    1.10
    С
    1.08
    POSITIVE LOGITS
    .}$
    1.56
    。“
    1.53
    v
    1.53
    ج
    1.52
    ર
    1.44
    .}
    1.41
    라면
    1.41
    ্তে
    1.35
    涳
    1.34
    .“
    1.34
    Act Density 0.631%

    No Known Activations