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

    Neuronpedia

    INDEX
    Explanations

    pl prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ket
    0.72
    யா
    0.67
    ある
    0.65
    yah
    0.63
     сово
    0.63
     体
    0.63
    相続
    0.62
     chance
    0.61
    ewhat
    0.61
     fast
    0.61
    POSITIVE LOGITS
    atform
    1.09
    agiarism
    1.03
     Pl
    1.02
    Pl
    1.02
    osion
    1.01
    äne
    0.99
    aintiff
    0.96
     Plat
    0.96
    acements
    0.94
    ausible
    0.94
    Act Density 0.035%

    No Known Activations