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

    Neuronpedia

    INDEX
    Explanations

    Code and Math

    np_max-act · gemini-2.0-flash

    phrases that involve odd and even numbers.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects the phrase pattern describing odd numbers in a group summing (“add up”) to an even total.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    //===
    -0.07
    	status
    -0.07
     wolves
    -0.06
     StringField
    -0.06
    ยก
    -0.06
    getStringExtra
    -0.06
    .getCmp
    -0.06
     dof
    -0.06
    -0.06
    noon
    -0.06
    POSITIVE LOGITS
    ekl
    0.06
    ζει
    0.06
    Neill
    0.06
    921
    0.06
    ified
    0.06
     Bau
    0.06
    'Neill
    0.06
     teleport
    0.06
    Gatt
    0.06
     poslední
    0.06
    Act Density 0.009%

    No Known Activations