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

    Neuronpedia

    INDEX
    Explanations

    HTML tags

    np_max-act · gemini-2.0-flash

    This neuron specifically fires on numeric literals—especially floating‐point values—in code or structured text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    细
    -0.07
     ikinci
    -0.06
     five
    -0.06
    ském
    -0.06
    497
    -0.06
    -proof
    -0.06
     üst
    -0.06
     mild
    -0.06
     že
    -0.06
     vivid
    -0.06
    POSITIVE LOGITS
     каб
    0.07
    object
    0.07
     IDb
    0.07
     pornofil
    0.07
     Interface
    0.06
     phil
    0.06
    Quality
    0.06
     Chancellor
    0.06
    getRepository
    0.06
    ErrorResponse
    0.06
    Act Density 0.076%

    No Known Activations