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

    Neuronpedia

    INDEX
    Explanations

    programming and math equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ataupun
    0.47
    iguë
    0.47
    ұл
    0.46
     somit
    0.46
    ahat
    0.45
    ajikan
    0.45
    alop
    0.44
     verfol
    0.43
    asarray
    0.43
    weekend
    0.43
    POSITIVE LOGITS
    وص
    0.42
     conf
    0.40
     Conf
    0.39
     bon
    0.38
    0
    0.38
     S
    0.38
    榴
    0.38
    テ
    0.37
     Sh
    0.37
     被
    0.37
    Act Density 0.004%

    No Known Activations