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

    Neuronpedia

    INDEX
    Explanations

    having a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ে
    1.26
    이란
    1.24
    ्मी
    1.20
    이
    1.18
    েরও
    1.18
     säga
    1.15
    篌
    1.13
     evolução
    1.12
     hausse
    1.09
     使い
    1.07
    POSITIVE LOGITS
    শিদ
    1.08
    Record
    1.02
     Record
    0.96
    istor
    0.96
    uger
    0.95
    ভান
    0.94
    Attendance
    0.94
    record
    0.92
     Excav
    0.92
    '^
    0.92
    Act Density 0.001%

    No Known Activations