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

    Neuronpedia

    INDEX
    Explanations

    Correctness

    np_max-act · gemini-2.0-flash

    statements evaluating correctness or accuracy of responses or decisions, including references to errors.

    oai_token-act-pair · gpt-5Triggered by @faiazazmain99

    words related to correctness, accuracy, or doing something right or wrong.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @faiazazmain99
    New Auto-Interp
    Negative Logits
    onis
    -0.27
    Ä°R
    -0.25
    TABLE
    -0.25
    bjerg
    -0.25
    wald
    -0.25
    æ³Ħæ¼ı
    -0.24
     hints
    -0.24
     pins
    -0.24
    çļĦç¨ĭ度
    -0.23
    Ł³
    -0.23
    POSITIVE LOGITS
     ere
    0.28
     validationResult
    0.26
     void
    0.26
    vier
    0.26
    ensen
    0.24
    该æ¡Ī
    0.24
    urn
    0.24
    èµ·è¯ī
    0.24
    è¿ijæľŁ
    0.24
     wake
    0.23
    Act Density 0.001%

    No Known Activations