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

    Neuronpedia

    INDEX
    Explanations

    variables and their derivatives in mathematical expressions

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

    variable t

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.60
    csolódó
    -0.56
     själva
    -0.48
    kaŭ
    -0.48
    allergenic
    -0.47
     nonUne
    -0.47
     setUp
    -0.46
    Failures
    -0.46
    rowable
    -0.45
    Преимущества
    -0.44
    POSITIVE LOGITS
     t
    0.75
     time
    0.60
    deltaTime
    0.57
    time
    0.57
    T
    0.56
    t
    0.54
    Time
    0.54
    DockStyle
    0.53
    TIME
    0.52
     Time
    0.50
    Act Density 0.125%

    No Known Activations