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

    Neuronpedia

    INDEX
    Explanations

    references to academic structure and organization

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

    abstract

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.58
    Kanpo
    -0.56
     continúas
    -0.56
     Majefty
    -0.54
    ariConfig
    -0.53
    ⓧ
    -0.50
    LabelTagHelper
    -0.49
    PageFactory
    -0.49
    internalType
    -0.48
    VolleyError
    -0.48
    POSITIVE LOGITS
    ArrowToggle
    0.42
     Meg
    0.37
     meg
    0.37
    Believe
    0.36
     Against
    0.36
    MOUS
    0.35
    ']],
    0.35
     Well
    0.35
    schuh
    0.35
     narrative
    0.35
    Act Density 0.124%

    No Known Activations