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

    Neuronpedia

    INDEX
    Explanations

    code boolean operators

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literal tokens (integers or floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    )`↵
    -0.07
    ;|
    -0.06
     |
    -0.06
    免费
    -0.06
    -स
    -0.06
     pills
    -0.06
    коз
    -0.06
     passes
    -0.06
    ました
    -0.06
     instantiated
    -0.06
    POSITIVE LOGITS
    obra
    0.08
     Exodus
    0.08
    Southern
    0.07
     Southern
    0.06
    yen
    0.06
    _boost
    0.06
     pás
    0.06
     catering
    0.06
     senior
    0.06
     Eisenhower
    0.06
    Act Density 0.051%

    No Known Activations