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

    Neuronpedia

    INDEX
    Explanations

    divide both sides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     তাপমাত্রা
    0.35
     수학
    0.35
    ubber
    0.34
     multiplicación
    0.34
    計算
    0.34
    畱
    0.34
    Мушко
    0.34
     বীজ
    0.33
    ફળ
    0.33
    枤
    0.33
    POSITIVE LOGITS
    an
    0.37
    "
    0.35
    u
    0.35
    #
    0.34
    ー
    0.34
    o
    0.33
    /
    0.33
    ・
    0.32
    ́
    0.31
     Orwell
    0.30
    Act Density 0.001%

    No Known Activations