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

    Neuronpedia

    INDEX
    Explanations

    serene mood, coherent text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    1.62
     on
    1.38
    h
    1.34
    v
    1.33
    d
    1.23
    ll
    1.14
    '
    1.14
     (
    1.13
     ऑन
    1.12
    ts
    1.11
    POSITIVE LOGITS
    দের
    1.19
    ای
    1.15
    月の
    1.15
    ५
    1.15
    지
    1.11
    μος
    1.09
    த்தில்
    1.09
     フランス
    1.08
    な
    1.08
    берриз
    1.07
    Act Density 0.065%

    No Known Activations