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

    Neuronpedia

    INDEX
    Explanations

    case

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric constants in code, especially floating-point literals.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     hep
    -0.07
    ']*
    -0.07
    ercise
    -0.06
    }-${
    -0.06
    ené
    -0.06
    旋
    -0.06
    ^.
    -0.06
     Ft
    -0.06
    Visualization
    -0.06
    keywords
    -0.06
    POSITIVE LOGITS
     immigrant
    0.07
    .attr
    0.06
    echn
    0.06
    คอม
    0.06
     radio
    0.06
    .auto
    0.06
    خاص
    0.06
    /example
    0.06
     może
    0.06
     çevir
    0.06
    Act Density 0.001%

    No Known Activations