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

    Neuronpedia

    INDEX
    Explanations

    characteristics related to imperfections and wear in products

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

    describing surface imperfections

    np_acts-logits-general · gemini-2.0-flash

    imperfections, marks, and sensations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.66
    ophysical
    -0.59
     TestBed
    -0.56
     implicitly
    -0.55
    ayakan
    -0.54
     administrative
    -0.52
     unlimited
    -0.51
    ligente
    -0.50
     Dummies
    -0.50
    swire
    -0.49
    POSITIVE LOGITS
     يتيمه
    0.68
    ElementException
    0.67
     caused
    0.62
     dû
    0.61
    RegressionTest
    0.61
    gefahr
    0.60
     underneath
    0.60
     caractéristique
    0.60
    évaluateur
    0.60
    hyrchwyd
    0.58
    Act Density 0.333%

    No Known Activations