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

    Neuronpedia

    INDEX
    Explanations

    common nouns and pronouns, particularly those indicating people and organizations

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

    Danish Holstein German

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.48
    లాలు
    -0.47
    Tembelea
    -0.46
    ViewFeatures
    -0.42
     computing
    -0.42
     capacity
    -0.41
     Computing
    -0.41
     property
    -0.41
     himo
    -0.41
     pool
    -0.39
    POSITIVE LOGITS
     betweenstory
    0.50
    RegressionTest
    0.49
    OGND
    0.45
    nyx
    0.44
    astéroïdes
    0.42
    ſt
    0.41
    ✢
    0.41
    tanleria
    0.40
    transQ
    0.40
    hoea
    0.40
    Act Density 0.008%

    No Known Activations