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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols used in complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Closing parentheses

    np_acts-logits-general · gemini-2.0-flash

    parenthesized lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.73
    ValueStyle
    -0.72
    出版年
    -0.71
     мәкал
    -0.70
     كومونز
    -0.68
     Minaj
    -0.65
    platin
    -0.65
     Administrativna
    -0.64
    Tikang
    -0.63
    UnusedPrivate
    -0.63
    POSITIVE LOGITS
     ).
    0.71
    ).
    0.70
    )).
    0.69
    ),
    0.68
    ()).
    0.67
    ))),
    0.67
     ),
    0.66
    ?).
    0.66
    ))).
    0.64
    })-\
    0.64
    Act Density 1.191%

    No Known Activations