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

    Neuronpedia

    INDEX
    Explanations

    manual vs automatic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bee
    0.53
    वण्यासाठी
    0.46
     り
    0.46
     loss
    0.45
     YOU
    0.45
     isotonic
    0.43
     abr
    0.42
     bộ
    0.41
     ໜ
    0.41
     reduction
    0.40
    POSITIVE LOGITS
    编码
    0.49
    kopp
    0.47
    atory
    0.45
    Uppercase
    0.45
    Paddle
    0.45
    ципа
    0.44
     funniest
    0.44
    paddle
    0.43
     stehen
    0.42
    film
    0.42
    Act Density 0.001%

    No Known Activations