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

    Neuronpedia

    INDEX
    Explanations

    at its core

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    逅
    2.18
    س
    2.09
    !/"
    2.04
     eisen
    1.79
    संपादन
    1.72
    "،
    1.72
     eli
    1.71
    $[
    1.70
     ",
    1.70
    ्यारह
    1.70
    POSITIVE LOGITS
    ுக்கு
    2.29
    ನ್
    2.12
    oost
    2.08
    ᇁ
    2.05
    หว่าง
    2.04
    sect
    1.95
    సక్తి
    1.93
    CLUSIVE
    1.93
    clus
    1.92
    ം
    1.88
    Act Density 0.165%

    No Known Activations