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

    Neuronpedia

    INDEX
    Explanations

    agenda and schedule

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    watch
    1.67
    0
    1.60
     이르
    1.55
    ainen
    1.50
     giây
    1.50
    к
    1.49
     sementara
    1.47
    TIP
    1.47
    ua
    1.46
    TRE
    1.46
    POSITIVE LOGITS
     perspici
    1.95
    ш
    1.86
    ור
    1.80
    ન
    1.80
    вам
    1.79
    ي
    1.79
    ماً
    1.77
    oje
    1.75
    ו
    1.73
     calendars
    1.70
    Act Density 0.041%

    No Known Activations