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

    Neuronpedia

    INDEX
    Explanations

    even though

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noise
    0.46
     arrested
    0.42
     stacked
    0.42
     arrest
    0.41
     grafik
    0.40
    ੁੱ
    0.40
     redundant
    0.39
    ಿತ್ತು
    0.38
    ischem
    0.38
     KPIs
    0.38
    POSITIVE LOGITS
     Für
    0.48
     خیلی
    0.47
     ചില
    0.44
    ມັນ
    0.44
    ینا
    0.44
    بی
    0.43
     പറഞ്ഞ
    0.43
    缀
    0.43
     маршру
    0.42
    Macro
    0.42
    Act Density 0.001%

    No Known Activations