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

    Neuronpedia

    INDEX
    Explanations

    made of, made up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    5
    0.46
    4
    0.44
    8
    0.43
     Buen
    0.43
    utilizzo
    0.43
    2
    0.42
    থার
    0.42
    ствием
    0.41
    are
    0.41
    $\
    0.41
    POSITIVE LOGITS
    leine
    0.67
     landfall
    0.50
     up
    0.45
    leva
    0.42
     radioactive
    0.41
     obsolete
    0.41
    atories
    0.40
     पू
    0.40
    zio
    0.39
    قف
    0.39
    Act Density 0.006%

    No Known Activations