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

    Neuronpedia

    INDEX
    Explanations

    primarily understand or json output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    icons
    0.58
    plings
    0.46
    CP
    0.45
    اق
    0.43
    挚
    0.42
    rol
    0.42
    نگ
    0.41
    Пол
    0.41
    ক্ষ
    0.41
     곡
    0.40
    POSITIVE LOGITS
     ALLO
    0.48
     beide
    0.46
     behaving
    0.46
     behave
    0.45
     redistribute
    0.44
     картина
    0.44
     να
    0.43
     continuación
    0.43
     Ellison
    0.43
     এখনই
    0.43
    Act Density 0.002%

    No Known Activations