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

    Neuronpedia

    INDEX
    Explanations

    measurement units and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    👁
    1.65
    Sarah
    1.60
    🥀
    1.54
     Sarah
    1.53
    🖇
    1.53
    🦦
    1.52
    LOTRE
    1.51
    🥁
    1.50
    ⏬
    1.48
    🤸
    1.47
    POSITIVE LOGITS
    気持ち
    0.67
    텐
    0.66
    ank
    0.64
    ंत
    0.64
    /
    0.63
    -
    0.61
    ¬
    0.61
    台上
    0.60
    निक
    0.59
    ↵
    0.58
    Act Density 0.020%

    No Known Activations