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

    Neuronpedia

    INDEX
    Explanations

    Width, 1

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric attribute values—especially floating-point numbers in XML tags (e.g. Android vector dimensions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .break
    -0.06
     Build
    -0.06
     Axel
    -0.06
     Taj
    -0.06
     AssertionError
    -0.06
     obras
    -0.06
     submits
    -0.06
     �
    -0.06
     utilizar
    -0.06
    <Form
    -0.06
    POSITIVE LOGITS
     udál
    0.07
     LIMITED
    0.06
     ATP
    0.06
    γει
    0.06
     millennia
    0.06
    NN
    0.06
     violently
    0.06
    _complete
    0.06
    MOST
    0.06
     multin
    0.06
    Act Density 0.001%

    No Known Activations