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

    Neuronpedia

    INDEX
    Explanations

    days of the week schedule

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مرکز
    0.39
    OnChange
    0.39
    ՞
    0.38
     include
    0.37
    Include
    0.36
    いっぱい
    0.36
    ካል
    0.36
     배경
    0.36
    boru
    0.36
    (__('
    0.36
    POSITIVE LOGITS
     suboptimal
    0.46
    ضيع
    0.44
     someday
    0.42
    economic
    0.39
    cedure
    0.38
     ఒక్క
    0.38
    有一天
    0.38
     यूं
    0.38
     ช่วย
    0.37
     cancelled
    0.37
    Act Density 0.000%

    No Known Activations