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

    Neuronpedia

    INDEX
    Explanations

    phrases describing the scope or severity of a situation or condition

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

    extent of or magnitude of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikimedijinoj
    -0.50
    FieldBuilder
    -0.45
    RegressionTest
    -0.44
    chased
    -0.44
    ientí
    -0.42
     chased
    -0.41
    таратура
    -0.41
     препратки
    -0.40
    thenReturn
    -0.40
    Vorte
    -0.40
    POSITIVE LOGITS
     severity
    0.71
     extent
    0.63
     Severity
    0.56
    Severity
    0.56
     Umfang
    0.54
     seriousness
    0.54
     Extent
    0.53
    imageshack
    0.52
    severity
    0.50
    saraba
    0.49
    Act Density 0.056%

    No Known Activations