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

    Neuronpedia

    INDEX
    Explanations

    scenarios and recommendations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    这也是
    0.47
     också
    0.47
     alas
    0.44
     tradition
    0.44
     accords
    0.44
     altid
    0.43
     oddly
    0.42
     neve
    0.41
     badly
    0.41
     sich
    0.40
    POSITIVE LOGITS
    ovi
    0.48
    ihu
    0.48
     Filipino
    0.46
    allowSlide
    0.46
    mysqli
    0.45
    ￫
    0.45
     уйнау
    0.45
    重新
    0.45
    Mozilla
    0.45
    лизова
    0.45
    Act Density 0.014%

    No Known Activations