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

    Neuronpedia

    INDEX
    Explanations

    lists of tools or items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    н
    0.95
    embal
    0.89
     hadi
    0.88
    ख
    0.83
    दा
    0.82
    无数
    0.82
    achsen
    0.82
    ocysts
    0.82
    නි
    0.80
    न
    0.80
    POSITIVE LOGITS
     وهذه
    0.78
     cuál
    0.75
     أجل
    0.75
     Владими
    0.75
    ों
    0.71
     Pars
    0.71
     Вас
    0.70
    mujer
    0.69
     Pareto
    0.68
     България
    0.68
    Act Density 0.003%

    No Known Activations