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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize identity and belonging

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

    what they truly are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    立
    -0.36
    ubat
    -0.35
    DISABLE
    -0.33
    aro
    -0.33
    ura
    -0.32
    op
    -0.32
    HStack
    -0.32
    arr
    -0.32
    los
    -0.32
    offsets
    -0.32
    POSITIVE LOGITS
    ConstraintMaker
    0.79
     kasarigan
    0.72
    Tembelea
    0.68
    脚注の使い方
    0.67
     يتيمه
    0.66
     المعيارى
    0.64
    OCCURRED
    0.63
    FunctionFlags
    0.59
    Diweddarwch
    0.59
     ujednoznacz
    0.58
    Act Density 0.033%

    No Known Activations