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

    Neuronpedia

    INDEX
    Explanations

    primordial, romance, premise, simultaneously, hemmed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ा
    0.55
    ामध्ये
    0.52
    hena
    0.45
    𒃲
    0.45
    اا
    0.45
    চ্ছন্ন
    0.43
    ﹰ
    0.43
    าน
    0.42
    لوان
    0.42
    तम
    0.42
    POSITIVE LOGITS
    atically
    1.07
    atic
    0.97
    ática
    0.96
    ageddon
    0.96
    ming
    0.90
    aterial
    0.87
    obile
    0.86
    pton
    0.86
    ichael
    0.86
    ático
    0.85
    Act Density 0.318%

    No Known Activations