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

    Neuronpedia

    INDEX
    Explanations

    AI models

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    un
    0.84
    ع
    0.83
    ६
    0.83
    nach
    0.82
    ｕ
    0.82
    𝐚
    0.80
    ａ
    0.80
    У
    0.79
    у
    0.79
    Ｓ
    0.79
    POSITIVE LOGITS
     té
    0.72
     rét
    0.65
     ederek
    0.64
     retard
    0.63
    pless
    0.62
     waardoor
    0.61
     स्त्रीलिंग
    0.61
     anges
    0.59
    áticas
    0.59
     hogs
    0.59
    Act Density 0.000%

    No Known Activations