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

    Neuronpedia

    INDEX
    Explanations

    references to specific figures and their contributions in a critical context

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

    Attribution of quotes or writings

    np_acts-logits-general · gemini-2.0-flash

    proper nouns writing or speaking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DebuggerNonUser
    -0.66
     مشين
    -0.64
     officielle
    -0.60
     ويكيميديا
    -0.56
     محفوظة
    -0.55
    kloped
    -0.54
     CreateTagHelper
    -0.53
    lotl
    -0.52
     impegno
    -0.52
     المعيارى
    -0.51
    POSITIVE LOGITS
     thesis
    0.53
     chas
    0.52
     Esq
    0.52
     Kluwer
    0.51
    cluye
    0.50
    Viitteet
    0.48
    RTGC
    0.48
    Schriften
    0.48
     sensei
    0.47
     propose
    0.46
    Act Density 0.420%

    No Known Activations