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

    Neuronpedia

    INDEX
    Explanations

    circle shape in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transom
    0.40
     ক্ষীণ
    0.40
     slender
    0.38
    騇
    0.38
    ocardi
    0.37
     pivots
    0.37
     ಆದ್ದರಿಂದ
    0.37
     گز
    0.37
    arote
    0.36
    ার্জন
    0.36
    POSITIVE LOGITS
    圆形
    1.00
     circular
    0.91
     Circular
    0.86
    圓
    0.83
    circular
    0.81
     tròn
    0.80
     circle
    0.79
    Circular
    0.77
     círculo
    0.77
     круг
    0.77
    Act Density 0.009%

    No Known Activations