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

    Neuronpedia

    INDEX
    Explanations

    references to postal addresses and box numbers

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

    box or nearest integer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    riwal
    -0.44
     useCallback
    -0.43
    يميديا
    -0.42
     nonatomic
    -0.41
    beitung
    -0.40
    krebs
    -0.40
     getResources
    -0.39
    tagHelperRunner
    -0.39
     <<<<<<<<<<<<<<
    -0.38
    pshire
    -0.38
    POSITIVE LOGITS
     Box
    1.34
     BOX
    1.18
     box
    1.09
    Box
    1.07
    BOX
    0.95
    box
    0.95
     Boxes
    0.95
     boxes
    0.94
    Boxes
    0.85
    boxes
    0.80
    Act Density 0.002%

    No Known Activations