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

    Neuronpedia

    INDEX
    Explanations

    sequences of code or data structures

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

    null bytes and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     оригіналу
    -0.53
     sumpay
    -0.51
    GOTREF
    -0.49
    IBOutlet
    -0.48
    outSlope
    -0.47
     ModelExpression
    -0.45
    EDEFAULT
    -0.45
    GTCX
    -0.44
     estekak
    -0.44
    complexContent
    -0.44
    POSITIVE LOGITS
    uxxxx
    0.57
     referrerpolicy
    0.49
    profiler
    0.43
     Session
    0.42
    keys
    0.42
     Zug
    0.41
    Session
    0.40
     Katrin
    0.40
    tonode
    0.40
     Augenblick
    0.40
    Act Density 0.102%

    No Known Activations