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

    Neuronpedia

    INDEX
    Explanations

    while

    np_max-act · gemini-2.0-flash

    The neuron detects numeric literal tokens—especially floating‐point constants—in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    れる
    -0.08
     phrases
    -0.07
    .getUserName
    -0.07
    uristic
    -0.07
    .Com
    -0.07
    ogen
    -0.06
    ?url
    -0.06
     Falling
    -0.06
    ORITY
    -0.06
     fingert
    -0.06
    POSITIVE LOGITS
    	while
    0.09
    _REMOVE
    0.07
    _wire
    0.07
    Console
    0.06
     wishlist
    0.06
     μέσα
    0.06
     withdraw
    0.06
     Mali
    0.06
     Clarence
    0.06
    hope
    0.06
    Act Density 0.005%

    No Known Activations