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

    Neuronpedia

    INDEX
    Explanations

    references to totality or completeness across various contexts

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

    completeness and extremity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    writeFieldEnd
    -0.49
     patern
    -0.48
    brary
    -0.47
     galle
    -0.45
     intersti
    -0.44
     Conſ
    -0.44
     raiſ
    -0.43
     domesti
    -0.43
     geng
    -0.42
     santi
    -0.41
    POSITIVE LOGITS
     totally
    0.84
     total
    0.82
     Totally
    0.80
     całkow
    0.80
     totale
    0.80
    totally
    0.78
    Totally
    0.78
     utterly
    0.77
     absolute
    0.77
    total
    0.77
    Act Density 0.066%

    No Known Activations