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

    Neuronpedia

    INDEX
    Explanations

    German patents

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens (especially floating‐point numbers or decimals).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Skyrim
    -0.07
     :↵↵
    -0.07
    什
    -0.07
     Enemy
    -0.06
    Teams
    -0.06
    Sub
    -0.06
    ों,
    -0.06
    Successful
    -0.06
     Hob
    -0.06
     Blades
    -0.06
    POSITIVE LOGITS
     greeted
    0.08
     official
    0.07
    uced
    0.07
     recruiter
    0.07
    adresse
    0.06
     Balanced
    0.06
     sitio
    0.06
    -cap
    0.06
     digestive
    0.06
     эк
    0.06
    Act Density 0.017%

    No Known Activations