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

    Neuronpedia

    INDEX
    Explanations

    disparaging words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pared
    0.44
     बुला
    0.40
    adip
    0.40
    parin
    0.39
    ayad
    0.38
     পায়ের
    0.38
     chromed
    0.37
     ديال
    0.37
     পাচ্ছি
    0.37
    ној
    0.37
    POSITIVE LOGITS
     Aging
    0.57
    Aging
    0.53
     aging
    0.50
    aging
    0.48
     Software
    0.44
    AGING
    0.43
    agement
    0.43
     ageing
    0.43
     یونی
    0.43
    AGER
    0.42
    Act Density 0.000%

    No Known Activations