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

    Neuronpedia

    INDEX
    Explanations

    became known

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     morales
    0.66
    gym
    0.65
     volna
    0.65
    ामुळे
    0.65
    dplyr
    0.62
     مساله
    0.61
    из
    0.60
    classifier
    0.60
    array
    0.59
    tikzpicture
    0.59
    POSITIVE LOGITS
    ة
    0.86
    лды
    0.77
    ah
    0.75
    िक
    0.71
    ção
    0.71
    ם
    0.70
    soever
    0.69
    larının
    0.68
    лы
    0.68
    ó
    0.68
    Act Density 0.001%

    No Known Activations