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

    Neuronpedia

    INDEX
    Explanations

    array access syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⬥
    0.48
     ({\
    0.48
     (’
    0.46
    }$-(
    0.45
     መድ
    0.44
    гән
    0.44
     (\<
    0.43
     (^{
    0.43
    ,(((
    0.43
    }({\
    0.43
    POSITIVE LOGITS
    [
    1.90
    [$
    1.34
    ['
    1.29
    [_
    1.29
    ["
    1.26
    ][
    1.25
    []
    1.25
    [\
    1.22
    [(
    1.17
    [-
    1.17
    Act Density 0.084%

    No Known Activations