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

    Neuronpedia

    INDEX
    Explanations

    起動次数

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ו
    1.05
    تى
    1.01
    ição
    0.98
    jà
    0.97
    ówn
    0.93
     pomocí
    0.90
     ativar
    0.89
    륵
    0.89
     músico
    0.89
    itarian
    0.88
    POSITIVE LOGITS
     clf
    1.07
    łeś
    1.06
     coasts
    1.05
     HMS
    1.03
    améli
    1.02
    스는
    1.02
    teddy
    1.01
     молока
    1.00
    쥐
    1.00
    轳
    0.98
    Act Density 0.001%

    No Known Activations