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

    Neuronpedia

    INDEX
    Explanations

    technical terms and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    의
    0.47
    များနှင့်
    0.47
     EU
    0.46
     from
    0.46
    },
    0.44
     payments
    0.43
     together
    0.43
     RA
    0.43
    နှင့်
    0.43
    weed
    0.43
    POSITIVE LOGITS
    жі
    0.55
     liegen
    0.50
    کنش
    0.50
    دع
    0.49
     gleich
    0.49
    اقة
    0.49
    Fernseh
    0.48
    اق
    0.47
    vagrant
    0.47
    يلة
    0.47
    Act Density 0.000%

    No Known Activations