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

    Neuronpedia

    INDEX
    Explanations

    cus, US, Kus, CUSIP

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     monitors
    0.45
     monit
    0.40
     мони
    0.39
    Hasher
    0.37
    ディスプレイ
    0.36
    लंघन
    0.36
     कच
    0.35
    ζ
    0.35
     Monitors
    0.35
     decouple
    0.35
    POSITIVE LOGITS
    appa
    0.43
     Cus
    0.43
     cus
    0.42
     জী
    0.42
     മൂല
    0.42
    ..\
    0.41
    cuss
    0.40
    akin
    0.38
    ostasis
    0.38
    app
    0.38
    Act Density 0.003%

    No Known Activations