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

    Neuronpedia

    INDEX
    Explanations

    various specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Роз
    0.43
    xe
    0.42
    Web
    0.38
    Us
    0.38
    [`
    0.38
    "`
    0.38
    Guard
    0.38
    Gü
    0.38
    Xe
    0.37
    Rest
    0.37
    POSITIVE LOGITS
     داعش
    0.50
     isoniazid
    0.46
    риал
    0.43
     azide
    0.42
     بابەت
    0.42
     imani
    0.42
     SIGN
    0.40
     Signup
    0.39
    是没有
    0.39
     אטאטורק
    0.39
    Act Density 0.000%

    No Known Activations