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

    Neuronpedia

    INDEX
    Explanations

    terms related to health, quality, and robustness in various contexts

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

    ending in "ness"

    np_acts-logits-general · gemini-2.0-flash

    strict warning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.83
     متعلقه
    -0.74
     يتيمه
    -0.74
     podjela
    -0.72
    quisa
    -0.71
    yntaxException
    -0.70
     виправивши
    -0.70
    IBarButtonItem
    -0.69
     noastre
    -0.68
    InSection
    -0.68
    POSITIVE LOGITS
    neſs
    0.77
     Bland
    0.70
    NESS
    0.68
    bland
    0.66
    enough
    0.65
    `"
    0.63
    ness
    0.63
    ()");
    0.62
    EROUS
    0.61
     Precise
    0.61
    Act Density 1.132%

    No Known Activations