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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values and measurements in a context

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

    Numbers followed by units or relative quantities

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by units or time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ItemBackground
    -0.79
     <<<<<<<<<<<<<<
    -0.73
    UnsafeEnabled
    -0.72
    LabelTagHelper
    -0.64
     geslacht
    -0.60
     aliqu
    -0.59
     ujednoznacz
    -0.59
     Winaray
    -0.58
    GeoNames
    -0.58
    KommentareTeilen
    -0.58
    POSITIVE LOGITS
    lynol
    0.56
    eroll
    0.52
     الساعة
    0.52
    logg
    0.49
    neth
    0.49
    )$-
    0.48
    typeorm
    0.48
    ology
    0.48
     '{@
    0.47
    tude
    0.47
    Act Density 0.356%

    No Known Activations