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

    Neuronpedia

    INDEX
    Explanations

    medical diagnosis and employment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     więc
    1.03
    ט
    1.01
    ätze
    0.94
     हस्त
    0.93
    𝑑
    0.91
     причины
    0.91
     gewähr
    0.89
     Polynomial
    0.89
    いろいろ
    0.89
    ènes
    0.89
    POSITIVE LOGITS
    rd
    1.18
     crucifix
    1.16
    rdquo
    1.16
    瓜
    1.11
    sticker
    1.09
    rte
    1.08
    갈
    1.07
    \'
    1.06
     condomin
    1.06
    ویں
    1.05
    Act Density 0.001%

    No Known Activations