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

    Neuronpedia

    INDEX
    Explanations

    elements related to serialized data structures or object representations

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

    OriginAirport; themselves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    again
    -0.63
    又
    -0.57
     again
    -0.55
     lagi
    -0.50
     又
    -0.47
     wieder
    -0.47
     опять
    -0.45
    Again
    -0.44
    又不
    -0.44
     yet
    -0.43
    POSITIVE LOGITS
     незавершена
    0.98
    RegressionTest
    0.79
    ⟬
    0.78
     المعيارى
    0.78
     itself
    0.75
     ब्रेकडाउन
    0.74
    parsedMessage
    0.73
     Wikimedijinoj
    0.73
     themselves
    0.72
     Infórmanos
    0.71
    Act Density 0.072%

    No Known Activations