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

    Neuronpedia

    INDEX
    Explanations

    references to the contents of entities or objects

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

    content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avoient
    -0.81
     étoient
    -0.73
     pouvoit
    -0.70
     feroit
    -0.68
     auroit
    -0.66
     enfans
    -0.63
    最快更新
    -0.59
     Obrador
    -0.59
    dersfield
    -0.59
    RegressionTest
    -0.59
    POSITIVE LOGITS
     containing
    0.55
     contents
    0.55
     Containing
    0.50
    containing
    0.48
     contain
    0.48
     contains
    0.48
     obsah
    0.47
    中身
    0.47
     innehå
    0.47
     Contains
    0.46
    Act Density 0.092%

    No Known Activations