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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash

    The neuron activates on floating-point numeric literals in source code (decimal numbers in assignments).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     HttpStatusCode
    -0.07
     ImmutableList
    -0.07
     latest
    -0.07
    _ELEMENT
    -0.06
    Male
    -0.06
    ROUGH
    -0.06
     cyl
    -0.06
    /prom
    -0.06
    _BIT
    -0.06
     dati
    -0.06
    POSITIVE LOGITS
    087
    0.07
    Applied
    0.06
    izziness
    0.06
    owe
    0.06
     Surg
    0.06
    _submission
    0.06
    elig
    0.06
     apro
    0.06
     Designs
    0.06
    便
    0.06
    Act Density 0.002%

    No Known Activations