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

    Neuronpedia

    INDEX
    Explanations

    terms related to evaluation and performance measurement in algorithms

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

    Followed by nouns

    np_acts-logits-general · gemini-2.0-flash

    key points, features, descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     larmes
    -0.62
     oreilles
    -0.62
     ***!
    -0.60
    "]));
    -0.58
     lèvres
    -0.58
     âmes
    -0.57
     незавершена
    -0.56
     виправивши
    -0.56
     '\\;'
    -0.55
     genoux
    -0.53
    POSITIVE LOGITS
     candidate
    0.75
    InitVars
    0.73
     observed
    0.69
     disambiguazione
    0.65
     query
    0.65
     training
    0.63
     predefined
    0.63
     input
    0.62
     user
    0.61
     observations
    0.61
    Act Density 1.473%

    No Known Activations