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

    Neuronpedia

    INDEX
    Explanations

    asterisk

    np_max-act · gemini-2.0-flash

    The neuron fires on floating-point numbers (decimal values) embedded in code comments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    specified
    -0.06
    ocrisy
    -0.06
    does
    -0.06
    Expected
    -0.06
     expected
    -0.06
     usando
    -0.06
     bold
    -0.06
     cst
    -0.06
    ;");↵
    -0.06
    Baseline
    -0.06
    POSITIVE LOGITS
     Musk
    0.07
     plata
    0.07
     rosa
    0.06
     Sink
    0.06
     standout
    0.06
     phoneNumber
    0.06
    щина
    0.06
    本当に
    0.06
    istorical
    0.06
    _offer
    0.06
    Act Density 0.012%

    No Known Activations