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

    Neuronpedia

    INDEX
    Explanations

    text and images as inputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apapun
    0.52
    ধ্বনি
    0.48
    เด
    0.48
    㓡
    0.46
    至于
    0.46
    AGING
    0.46
    OCI
    0.45
    itudinal
    0.45
    𠃍
    0.45
    背后
    0.45
    POSITIVE LOGITS
     Geme
    0.46
     Virg
    0.45
    q
    0.43
    brix
    0.42
     Bec
    0.41
     моде
    0.41
    unfinished
    0.41
    live
    0.41
    thed
    0.41
     new
    0.40
    Act Density 0.003%

    No Known Activations