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

    Neuronpedia

    INDEX
    Explanations

    academic and publication-related references or citations

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

    journal citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsContent
    -0.53
     endfor
    -0.51
     queſta
    -0.50
    +#+#
    -0.50
    HasForeignKey
    -0.50
    bootstrapcdn
    -0.49
     للمعارف
    -0.47
     المعيارى
    -0.47
    (___
    -0.47
    AnimationsModule
    -0.46
    POSITIVE LOGITS
    OGND
    0.54
     espoir
    0.40
     ucapnya
    0.40
     oculto
    0.39
     Perlu
    0.38
     marcado
    0.36
     revisar
    0.36
     Semoga
    0.35
     duquel
    0.35
     pungkas
    0.35
    Act Density 0.154%

    No Known Activations