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

    Neuronpedia

    INDEX
    Explanations

    cases and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     перспекти
    0.70
     мебели
    0.69
     формата
    0.66
     би
    0.66
     екс
    0.64
     целе
    0.64
     séquence
    0.63
     периоди
    0.62
     беше
    0.61
     литера
    0.61
    POSITIVE LOGITS
    hent
    0.73
    ח
    0.70
    Class
    0.64
    ку
    0.63
    ע
    0.63
    ust
    0.59
    }=
    0.59
    io
    0.58
    add
    0.58
    RS
    0.58
    Act Density 0.001%

    No Known Activations