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

    Neuronpedia

    INDEX
    Explanations

    thinness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ین
    1.14
    til
    1.02
    t
    0.93
    to
    0.89
    till
    0.86
     bunyi
    0.85
    вых
    0.85
     and
    0.84
    tic
    0.84
    ве
    0.83
    POSITIVE LOGITS
    at
    1.39
    薄
    1.31
    ا
    1.30
     thin
    1.16
    。
    1.11
    很
    1.06
     thinner
    1.05
     Thin
    1.03
    Thin
    0.97
    د
    0.97
    Act Density 0.025%

    No Known Activations