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

    Neuronpedia

    INDEX
    Explanations

    code block delimiters and terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    란
    0.41
     FS
    0.38
     asymmetrical
    0.38
    ྫ
    0.38
     paragraph
    0.38
    ਥ
    0.38
     '!
    0.37
     tiende
    0.37
     aliran
    0.37
    คโนโล
    0.37
    POSITIVE LOGITS
    है
    0.38
     টিকিট
    0.37
    खड़
    0.36
    avip
    0.36
    ⒉
    0.36
     বেড়
    0.35
    ونکو
    0.35
    autista
    0.35
     शै
    0.35
    长老
    0.34
    Act Density 0.004%

    No Known Activations