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

    Neuronpedia

    INDEX
    Explanations

    code and data

    np_max-act · gemini-2.0-flash

    The neuron flags floating‐point numerals (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (levels
    -0.07
    ДК
    -0.07
     přij
    -0.06
    upd
    -0.06
     cof
    -0.06
    CHA
    -0.06
    LD
    -0.06
    ells
    -0.06
     همان
    -0.06
     апп
    -0.06
    POSITIVE LOGITS
     night
    0.07
     Night
    0.07
     Sheffield
    0.06
     gif
    0.06
    _cube
    0.06
     useHistory
    0.06
    EventArgs
    0.06
     bowling
    0.06
    INSTANCE
    0.06
     Database
    0.06
    Act Density 0.002%

    No Known Activations