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

    Neuronpedia

    INDEX
    Explanations

    Exponents expressed as asterisks

    np_max-act · gemini-2.0-flash

    This neuron detects the use of algebraic operators for multiplication and exponentiation (e.g. “*” and “**”) in mathematical expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Motor
    -0.06
    successfully
    -0.06
    compass
    -0.06
     již
    -0.06
    addons
    -0.06
     пацієн
    -0.06
    uggage
    -0.06
    generated
    -0.06
     graduation
    -0.06
    電
    -0.06
    POSITIVE LOGITS
     Howell
    0.07
     Palin
    0.07
    ensburg
    0.07
     :=
    0.06
    Watcher
    0.06
     dép
    0.06
    ={$
    0.06
     =↵↵
    0.06
     حسين
    0.06
     Ying
    0.06
    Act Density 0.009%

    No Known Activations