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

    Neuronpedia

    INDEX
    Explanations

    breasts, face, cm, offer, breakfast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    1.01
    emper
    0.94
     нажмите
    0.92
    IK
    0.90
     '
    0.86
     эк
    0.85
     бывает
    0.85
    с
    0.85
     новым
    0.82
     совсем
    0.81
    POSITIVE LOGITS
    كة
    0.86
    الص
    0.82
    ‌ها
    0.80
    aithe
    0.79
     Khanna
    0.78
    Während
    0.78
     persu
    0.77
    หญิง
    0.77
    Katie
    0.77
    Contrary
    0.77
    Act Density 0.001%

    No Known Activations