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

    Neuronpedia

    INDEX
    Explanations

    Slack platform and API

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    0.75
    жет
    0.70
    t
    0.70
    کریاں
    0.68
    羟
    0.67
    ст
    0.67
    와
    0.66
     шуда
    0.65
    انی
    0.64
    ත්
    0.64
    POSITIVE LOGITS
    م
    1.05
     as
    0.90
    مي
    0.89
     wohl
    0.85
    OS
    0.83
     are
    0.77
    。
    0.77
    ع
    0.77
    re
    0.75
    ين
    0.75
    Act Density 0.002%

    No Known Activations