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

    Neuronpedia

    INDEX
    Explanations

    discussions of software features and performance comparisons

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

    solving problemssetting goalsaiming for somethinggetting things rightaddressing issuescompeting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.52
     tatuaje
    -0.49
    fjspx
    -0.49
    RectangleBorder
    -0.48
     Paglinawan
    -0.48
    TagHelper
    -0.47
    ſelf
    -0.46
     tours
    -0.45
     unknownFields
    -0.45
    ftagPool
    -0.45
    POSITIVE LOGITS
    wapV
    0.40
    .*")]
    0.40
    äuser
    0.40
    jarat
    0.38
     sahip
    0.38
    phem
    0.37
     հղումներ
    0.37
    ۣ
    0.36
    HomeAsUp
    0.36
    fos
    0.36
    Act Density 0.314%

    No Known Activations