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

    Neuronpedia

    INDEX
    Explanations

    shuffle / shuffling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ların
    1.30
    s
    1.30
    ss
    1.25
    sa
    1.20
    sp
    1.19
    ni
    1.18
     a
    1.13
    ny
    1.09
    sl
    1.07
    sh
    1.03
    POSITIVE LOGITS
    ي
    1.06
    ر
    1.05
    র
    0.96
    ብስ
    0.93
    ógrafo
    0.93
     jugador
    0.92
    י
    0.92
    บ
    0.89
     compléter
    0.89
     provincia
    0.86
    Act Density 0.024%

    No Known Activations