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

    Neuronpedia

    INDEX
    Explanations

    numbers and codes including 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.66
     is
    0.57
     organis
    0.52
     amulet
    0.52
    ;
    0.49
     auteur
    0.49
     I
    0.48
     ornith
    0.47
     ABV
    0.46
     arab
    0.46
    POSITIVE LOGITS
    and
    0.69
    на
    0.66
    い
    0.66
    ла
    0.65
    나
    0.63
    다
    0.59
    り
    0.58
    nd
    0.57
    いを
    0.56
    2
    0.56
    Act Density 0.336%

    No Known Activations