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

    Neuronpedia

    INDEX
    Explanations

    numeric values and references to data or results

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

    Appears before a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    Senator or suburbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     оно
    -0.92
     Оно
    -0.77
     it
    -0.75
    它
    -0.73
     ervan
    -0.73
     daarvan
    -0.72
     ň
    -0.72
     它
    -0.70
     dermed
    -0.68
    それが
    -0.68
    POSITIVE LOGITS
    WriteTagHelper
    0.78
    withstanding
    0.74
     Regarding
    0.69
     Paglinawan
    0.68
     referenties
    0.67
    ंदीखरीदारी
    0.65
    Regarding
    0.64
    Facades
    0.64
    contentLoaded
    0.63
     Apart
    0.63
    Act Density 0.416%

    No Known Activations