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

    Neuronpedia

    INDEX
    Explanations

    generality

    np_max-act · gemini-2.0-flash

    This neuron fires on decimal numeric values (floating-point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    rive
    -0.07
    passes
    -0.06
     capsule
    -0.06
    ziehung
    -0.06
     embracing
    -0.06
    hardware
    -0.06
    /location
    -0.06
    train
    -0.06
     Fransa
    -0.05
     zie
    -0.05
    POSITIVE LOGITS
     предел
    0.07
     hương
    0.07
     stanov
    0.07
    favicon
    0.06
    .channel
    0.06
     natur
    0.06
    <Resource
    0.06
    polate
    0.06
    :boolean
    0.06
    ={{
    0.06
    Act Density 0.112%

    No Known Activations