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

    Neuronpedia

    INDEX
    Explanations

    demographics and customer focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Thousands
    0.40
     Hundreds
    0.38
    राधिक
    0.38
    Thousands
    0.38
    CLR
    0.37
    Severe
    0.37
    Those
    0.36
     বাড়
    0.36
    those
    0.36
    வருக்கு
    0.36
    POSITIVE LOGITS
    iren
    0.45
     sweetest
    0.44
     fashioned
    0.44
     等
    0.41
     cutest
    0.40
    لوان
    0.39
    fashioned
    0.39
     niest
    0.39
     Kat
    0.38
    冯
    0.38
    Act Density 0.002%

    No Known Activations