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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literals (especially floating-point constants) in source code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     commitment
    -0.07
    _cou
    -0.07
    rag
    -0.07
    NoSuch
    -0.06
    extend
    -0.06
    	gui
    -0.06
    ')."
    -0.06
    лада
    -0.06
    .cli
    -0.06
    .her
    -0.06
    POSITIVE LOGITS
    fon
    0.07
    (@
    0.06
     fined
    0.06
    andbox
    0.06
    ыс
    0.06
     lush
    0.06
     starvation
    0.06
    _arm
    0.06
     assigned
    0.06
     kvm
    0.06
    Act Density 0.006%

    No Known Activations