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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric version‐number tokens (i.e. decimal numbers in assembly or config version attributes).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	freopen
    -0.06
    Fail
    -0.06
     logits
    -0.06
    avra
    -0.06
    会议
    -0.06
    )]↵
    -0.06
     Script
    -0.06
     Devon
    -0.05
    _ulong
    -0.05
    {}_
    -0.05
    POSITIVE LOGITS
     перемен
    0.07
    ancements
    0.07
     mt
    0.07
    ิตภ
    0.07
    0.06
    modo
    0.06
    ROLE
    0.06
     Hollande
    0.06
     shipments
    0.06
     −
    0.06
    Act Density 0.002%

    No Known Activations