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

    Neuronpedia

    INDEX
    Explanations

    powers of 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conund
    0.47
    inosaur
    0.45
    പ്പി
    0.45
    位数
    0.44
    বছ
    0.44
    +#+#
    0.44
    stringProp
    0.43
    Ш
    0.43
    yard
    0.43
     CORPER
    0.42
    POSITIVE LOGITS
    Tá
    0.63
     spoj
    0.59
    χής
    0.54
    Plants
    0.53
    Pog
    0.53
    ри
    0.52
    baikan
    0.52
     backcountry
    0.52
    znacz
    0.51
    )[
    0.50
    Act Density 0.000%

    No Known Activations