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

    Neuronpedia

    INDEX
    Explanations

    EEOC employment regulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.94
    on
    0.93
    ut
    0.87
    il
    0.80
    y
    0.80
    i
    0.79
    ت
    0.79
    ن
    0.76
    ED
    0.75
    yang
    0.73
    POSITIVE LOGITS
     Tattha
    0.68
     Букмекердик
    0.61
     gahet
    0.60
     niet
    0.59
    ಕ್ಕಿಂತ
    0.59
     hük
    0.57
     phép
    0.57
     Navarro
    0.57
     Geschmack
    0.57
    獲
    0.57
    Act Density 0.001%

    No Known Activations