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

    Neuronpedia

    INDEX
    Explanations

    master data view

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dc
    0.44
     dangerous
    0.42
    探
    0.42
    designed
    0.42
     टक
    0.41
     eminently
    0.41
     ބ
    0.40
    ond
    0.40
    独立
    0.40
    extremely
    0.40
    POSITIVE LOGITS
     SplashScreen
    0.53
     Physiology
    0.46
     lecithin
    0.45
     saldo
    0.45
    oitte
    0.44
    quier
    0.44
    ğun
    0.43
    িশালী
    0.43
     Mitgl
    0.42
     juc
    0.42
    Act Density 0.001%

    No Known Activations