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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific measurements or parameters

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

    SPIE papers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vuestros
    -0.33
     Weisheit
    -0.32
    Tudo
    -0.31
     pungkasnya
    -0.30
     billetes
    -0.30
    حث
    -0.28
    équi
    -0.27
    uduk
    -0.26
     usia
    -0.26
     deseas
    -0.25
    POSITIVE LOGITS
     <=",
    0.63
    featureID
    0.63
     ―――――
    0.61
     ivelany
    0.61
    GEBURTSDATUM
    0.60
    нгред
    0.60
    AddTagHelper
    0.59
    AddAttribute
    0.59
     nakalista
    0.59
     NSCoder
    0.59
    Act Density 0.191%

    No Known Activations