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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     பூஜ
    0.88
    POD
    0.73
     الحلقه
    0.72
     उद्यान
    0.68
    Episode
    0.68
    Attendance
    0.67
    ducted
    0.67
    ◟
    0.66
    aub
    0.66
     pasien
    0.65
    POSITIVE LOGITS
     Got
    0.65
    ското
    0.63
     brake
    0.63
    蒙
    0.63
     moral
    0.62
    otip
    0.61
    onitrile
    0.60
     Blocks
    0.59
     antidepressant
    0.59
    itimate
    0.59
    Act Density 0.001%

    No Known Activations