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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    This neuron detects numeric confidence/cost values (decimal numbers) in the ASR hypothesis listings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     arteries
    -0.06
    opening
    -0.06
    _created
    -0.06
    Demand
    -0.06
    acades
    -0.06
     Opening
    -0.06
     Laravel
    -0.06
    اضی
    -0.06
     cherry
    -0.05
    -dependent
    -0.05
    POSITIVE LOGITS
     edip
    0.08
    .";↵
    0.08
    .turn
    0.07
    로그램
    0.07
    "]["
    0.07
     ülke
    0.07
    -Bar
    0.06
     zorunlu
    0.06
     ".");↵
    0.06
     independently
    0.06
    Act Density 0.014%

    No Known Activations