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

    Neuronpedia

    INDEX
    Explanations

    traceable test cases or systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    峄
    0.54
    риал
    0.54
     腰
    0.53
    唵
    0.53
     божомол
    0.52
     gorges
    0.52
     ഭക്ഷണം
    0.51
    ђено
    0.51
    ປະ
    0.50
     KZ
    0.50
    POSITIVE LOGITS
    an
    0.61
    s
    0.59
    in
    0.59
    ac
    0.49
    -
    0.47
    te
    0.47
    ch
    0.46
     log
    0.45
     a
    0.45
    ate
    0.45
    Act Density 0.002%

    No Known Activations