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

    Neuronpedia

    INDEX
    Explanations

    also

    np_acts-logits-general · gemini-2.5-flash-lite

    also followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    0.73
     anteced
    0.71
    𝟯
    0.70
    ע
    0.70
    し
    0.66
    নে
    0.66
    jší
    0.66
     loafers
    0.66
    -
    0.65
    ਮ
    0.65
    POSITIVE LOGITS
     to
    1.02
    t
    0.90
    то
    0.79
    <0x80>
    0.76
    с
    0.74
    да
    0.73
    ></
    0.73
     (
    0.72
    на
    0.72
    h
    0.69
    Act Density 1.267%

    No Known Activations