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

    Neuronpedia

    INDEX
    Explanations

    Programming/technical documentation

    np_max-act · gemini-2.0-flash

    This neuron detects floating-point numeric literals (decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    anooga
    -0.07
     yaml
    -0.07
     Leonard
    -0.07
    ugged
    -0.07
    /%
    -0.06
     첫
    -0.06
    .Le
    -0.06
     pillar
    -0.06
     Minor
    -0.06
     boiled
    -0.06
    POSITIVE LOGITS
     přisp
    0.08
    化学
    0.06
    ็นการ
    0.06
     NGX
    0.06
    зна
    0.06
    rah
    0.06
    ;n
    0.06
    _clusters
    0.06
     TArray
    0.06
    Marca
    0.06
    Act Density 0.067%

    No Known Activations