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

    Neuronpedia

    INDEX
    Explanations

    first, followed by comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ками
    2.77
    2.75
    2.61
    2.57
    蒻
    2.50
    াড়ি
    2.47
    एस
    2.44
    kaan
    2.41
    2.41
    actionMode
    2.38
    POSITIVE LOGITS
    y
    2.17
    𝙙
    2.05
    oer
    2.03
    eniu
    1.98
    𝙣
    1.98
    𝙮
    1.97
    𝙧
    1.92
    𝙩
    1.81
    entr
    1.78
    STAND
    1.74
    Act Density 1.420%

    No Known Activations