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

    Neuronpedia

    INDEX
    Explanations

    start of sentence punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.42
     ١
    0.35
    on
    0.32
    }$;
    0.32
    n
    0.31
     ٢
    0.30
    なども
    0.30
     percentuale
    0.29
    '
    0.29
    ↵↵
    0.29
    POSITIVE LOGITS
    𝗴
    0.38
     has
    0.37
     have
    0.35
    pessoas
    0.34
    वेयर
    0.32
     volunteering
    0.31
    वासीय
    0.31
    investissement
    0.30
    ಗಳು
    0.30
     चिकित्सा
    0.30
    Act Density 7.663%

    No Known Activations