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

    Neuronpedia

    INDEX
    Explanations

    quantity or degree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bliss
    0.47
     demás
    0.46
     tomado
    0.43
     மேலும்
    0.42
    一定
    0.42
     siendo
    0.41
     confocal
    0.41
     infinitely
    0.41
     kohta
    0.41
     somehow
    0.39
    POSITIVE LOGITS
    ú
    0.57
    räume
    0.56
    neſs
    0.56
    ă
    0.53
    ル
    0.53
    issime
    0.52
    soort
    0.52
    rène
    0.52
    āda
    0.51
    rát
    0.51
    Act Density 0.893%

    No Known Activations