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

    Neuronpedia

    INDEX
    Explanations

    the start of a document or significant sections within it

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

    Code snippets and uncommon punctuation

    np_acts-logits-general · gemini-2.0-flash

    contrasting conjunctions and subsequent identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    intellij
    -0.52
    าท
    -0.51
     prior
    -0.51
     similarly
    -0.51
     la
    -0.50
    atte
    -0.49
     and
    -0.49
    gi
    -0.49
    dziew
    -0.48
    readdir
    -0.48
    POSITIVE LOGITS
    }));
    0.93
    ')")
    0.91
     Theſe
    0.90
    };*/
    0.90
    )')
    0.88
    }])
    0.87
    }))
    0.85
    )");
    0.85
    ]));
    0.84
    '}>
    0.83
    Act Density 0.013%

    No Known Activations