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

    Neuronpedia

    INDEX
    Explanations

    service descriptions

    np_max-act · gemini-2.0-flash

    This neuron detects words related to programming compilation and transpilation (e.g. “código,” “compilación,” “transpilación”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ává
    -0.07
     tasted
    -0.07
    <unsigned
    -0.07
    _temperature
    -0.06
     ува
    -0.06
     Calvin
    -0.06
    @Getter
    -0.06
    testCase
    -0.06
    温度
    -0.06
     inflate
    -0.06
    POSITIVE LOGITS
    (&___
    0.07
     Scre
    0.06
    ickými
    0.06
     lax
    0.06
    ValueGenerationStrategy
    0.06
    _BROWSER
    0.06
     catchy
    0.06
    ULLET
    0.06
     ACTIONS
    0.06
     WD
    0.06
    Act Density 0.119%

    No Known Activations