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

    Neuronpedia

    INDEX
    Explanations

    noodles, ribbons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    swith
    0.95
    ান
    0.89
    মা
    0.88
    ynomial
    0.88
    ৈ
    0.87
    싶
    0.87
    েন্সি
    0.87
    تی
    0.86
    ার
    0.86
    ろしく
    0.85
    POSITIVE LOGITS
     brakes
    0.98
     tę
    0.98
    ential
    0.97
     основ
    0.95
    küm
    0.93
     Labrenzia
    0.91
     уте
    0.89
    бліоте
    0.88
     gesamte
    0.88
    ্বাদ
    0.88
    Act Density 0.070%

    No Known Activations