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

    Neuronpedia

    INDEX
    Explanations

    activities and their outputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ال
    0.59
    j
    0.56
    بي
    0.54
    ط
    0.54
    im
    0.53
    يل
    0.53
     is
    0.52
    ש
    0.52
     كه
    0.51
     جديد
    0.50
    POSITIVE LOGITS
    yta
    0.60
    <0xA1>
    0.47
    нів
    0.46
     AcOH
    0.44
    InfoPlistPath
    0.44
    yue
    0.44
     ১৩২১
    0.43
    टान
    0.43
     Appointments
    0.43
     १८४
    0.43
    Act Density 0.540%

    No Known Activations