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

    Neuronpedia

    INDEX
    Explanations

    specific numerical and evaluative metrics related to performance and comparisons

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

    measured, relative, difference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Derbyniad
    -0.36
    ๆ
    -0.30
     otra
    -0.29
    AnimationsModule
    -0.29
     joão
    -0.29
     AssemblyTitle
    -0.28
     كورة
    -0.27
    平
    -0.27
    ・
    -0.27
     nuevamente
    -0.27
    POSITIVE LOGITS
    addPreferredGap
    0.67
     InputDecoration
    0.61
    Personensuche
    0.60
    脚注の使い方
    0.58
    IsMutable
    0.57
    parsedMessage
    0.57
     yyr
    0.55
     nakalista
    0.54
    offsetof
    0.53
    rmtree
    0.52
    Act Density 0.149%

    No Known Activations