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

    Neuronpedia

    INDEX
    Explanations

    about insecurity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مناسب
    0.46
    el
    0.45
    us
    0.44
     ساز
    0.42
    uss
    0.41
    osity
    0.41
    0.40
    es
    0.40
    Matches
    0.39
    ous
    0.39
    POSITIVE LOGITS
     recognise
    0.52
     фотографи
    0.51
     yüzde
    0.51
     fotografías
    0.51
     După
    0.50
    写真を
    0.50
     avocados
    0.49
    корд
    0.49
    profen
    0.48
    केर
    0.47
    Act Density 0.004%

    No Known Activations