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

    Neuronpedia

    INDEX
    Explanations

    XML namespace declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     legitim
    0.80
    h
    0.75
     entrer
    0.71
    In
    0.69
     liber
    0.69
    He
    0.67
    s
    0.65
     equipe
    0.64
    i
    0.64
     reconocido
    0.62
    POSITIVE LOGITS
    ла
    0.91
    ಾ
    0.78
    وک
    0.77
    ş
    0.77
    व्ह
    0.75
    ो
    0.74
    ن
    0.73
    न
    0.72
    ഡ്
    0.72
    ш
    0.71
    Act Density 0.001%

    No Known Activations