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

    Neuronpedia

    INDEX
    Explanations

    terms related to precision and accuracy in descriptions or analyses

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

    precision and accuracy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.56
    Kanpo
    -0.48
     Belajar
    -0.47
    deelte
    -0.47
     Withers
    -0.42
    Fordítás
    -0.42
     Cotter
    -0.41
     fuertemente
    -0.41
    adaptiveStyles
    -0.40
    handleRequest
    -0.40
    POSITIVE LOGITS
    precise
    1.28
     precise
    1.23
    accurate
    1.21
    Precise
    1.20
     Accurate
    1.20
    Accurate
    1.19
     Precise
    1.16
     accurate
    1.16
     exact
    1.16
     precision
    1.16
    Act Density 0.044%

    No Known Activations