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

    Neuronpedia

    INDEX
    Explanations

    colon followed by parentheses or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Precious
    0.49
     Lyft
    0.46
     ケ
    0.43
    お子
    0.43
    urger
    0.42
    oly
    0.42
    ressing
    0.41
     Occasionally
    0.41
     Older
    0.40
    rese
    0.40
    POSITIVE LOGITS
    ويم
    0.53
    ל
    0.53
    었다
    0.47
    عيد
    0.47
    𝖒
    0.47
    ായി
    0.46
     svim
    0.46
    𝖑
    0.46
    プーン
    0.46
     lakini
    0.46
    Act Density 0.000%

    No Known Activations