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

    Neuronpedia

    INDEX
    Explanations

    date or event happened

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ीन
    2.58
    ी
    2.51
    া
    2.41
    ي
    2.13
    ◀
    2.12
     Certainly
    2.10
    們
    2.10
    कों
    2.09
    NSLog
    2.08
     сразу
    2.07
    POSITIVE LOGITS
     potem
    2.52
     luego
    2.37
    ح
    2.29
    ive
    2.20
    с
    2.08
    \%
    2.01
    𝘮
    1.90
    ע
    1.87
    𝘯
    1.83
     ′
    1.83
    Act Density 0.008%

    No Known Activations