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

    Neuronpedia

    INDEX
    Explanations

    measurements and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    らっしゃる
    0.48
    ℂ
    0.48
    ｲ
    0.47
    Ⴚ
    0.47
     モダン
    0.47
    Ⅽ
    0.46
    ﾙ
    0.46
    烔
    0.46
    フィック
    0.45
    convolve
    0.45
    POSITIVE LOGITS
     API
    0.48
     Lottery
    0.47
     Blo
    0.47
     Dig
    0.46
     access
    0.46
     UI
    0.46
     checkpoints
    0.46
     Pr
    0.46
     Program
    0.45
     Pi
    0.45
    Act Density 0.001%

    No Known Activations