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

    Neuronpedia

    INDEX
    Explanations

    questions and commands that initiate dialogue or inquiry

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

    Question beginning with "Do"

    np_acts-logits-general · gemini-2.0-flash

    do you think

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedCtor
    -0.74
    AndEndTag
    -0.71
    -0.68
    :✨
    -0.67
    RenderAtEndOf
    -0.67
    gameserver
    -0.66
    EndProject
    -0.64
    LabelTagHelper
    -0.63
    GIVEREF
    -0.63
    SharedDtor
    -0.61
    POSITIVE LOGITS
    omsday
    0.68
    zens
    0.67
     I
    0.64
     want
    0.62
     they
    0.60
     we
    0.59
     remember
    0.59
     know
    0.58
    lores
    0.58
    berman
    0.57
    Act Density 0.051%

    No Known Activations