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

    Neuronpedia

    INDEX
    Explanations

    ideal following quote, day, scenario, or for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ва
    1.30
    та
    1.27
     tendre
    1.27
    ста
    1.24
    d
    1.24
    на
    1.23
    ᔨ
    1.19
    ins
    1.18
    可以
    1.17
    j
    1.17
    POSITIVE LOGITS
    BI
    1.34
    ς
    1.25
    LE
    1.23
    GA
    1.23
    ee
    1.08
    ことが多い
    1.06
    ি
    1.06
    CH
    1.04
    Input
    1.04
     Populate
    1.04
    Act Density 0.170%

    No Known Activations