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

    Neuronpedia

    INDEX
    Explanations

    terms related to performance evaluations and metrics

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

    "performance"

    np_acts-logits-general · gemini-2.0-flash

    performance of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nacionales
    -0.48
     subsidy
    -0.45
     Cientí
    -0.45
     raiz
    -0.39
     vuestros
    -0.39
     necessários
    -0.39
    Lunes
    -0.39
     Wilayah
    -0.39
     Sociales
    -0.39
    2
    -0.39
    POSITIVE LOGITS
     performance
    1.20
    performance
    1.15
     Performance
    1.13
     performances
    1.11
    Performance
    1.06
     Performances
    1.03
     PERFORMANCE
    0.98
    perform
    0.97
    PERFORMANCE
    0.97
    Performances
    0.91
    Act Density 0.089%

    No Known Activations