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

    Neuronpedia

    INDEX
    Explanations

    scripts:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     কতক
    0.58
    ně
    0.58
    sleeping
    0.57
    ushal
    0.56
    ě
    0.54
    ्यारह
    0.53
    ネ
    0.52
    гети
    0.52
    示す
    0.52
    *',
    0.52
    POSITIVE LOGITS
    ق
    0.78
     должен
    0.68
     interfacial
    0.67
     onboarding
    0.64
    ing
    0.62
     Miramar
    0.60
     transfert
    0.60
     autocl
    0.60
     interdiscipl
    0.59
     fling
    0.59
    Act Density 0.000%

    No Known Activations