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

    Neuronpedia

    INDEX
    Explanations

    ton

    np_max-act · gemini-2.0-flash

    The neuron appears to be completely inactive (it does not respond to any tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Belmont
    -0.06
    uilt
    -0.06
     окт
    -0.06
    ává
    -0.06
    icing
    -0.06
     react
    -0.06
    _mappings
    -0.06
    inding
    -0.06
     tips
    -0.05
    lection
    -0.05
    POSITIVE LOGITS
     recep
    0.07
    лишком
    0.07
    рет
    0.07
    感到
    0.06
    401
    0.06
     možnost
    0.06
     executed
    0.06
    [date
    0.06
     možné
    0.06
    paths
    0.06
    Act Density 0.004%

    No Known Activations