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

    Neuronpedia

    INDEX
    Explanations

    cute, lovely descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🛐
    0.41
    Careers
    0.40
     ಸಲ್ಲ
    0.40
    বৈশাখ
    0.40
     دس
    0.40
    Perfect
    0.39
     করছি
    0.39
    ર્મ
    0.39
    感慨
    0.39
     مصرى
    0.39
    POSITIVE LOGITS
     cute
    1.09
    可爱
    1.08
     Cute
    0.96
    可愛
    0.93
     lovely
    0.92
     adorable
    0.90
    Cute
    0.88
     cutest
    0.86
     naughty
    0.86
    cute
    0.86
    Act Density 0.005%

    No Known Activations