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

    Neuronpedia

    INDEX
    Explanations

    difference

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the word “difference,” i.e. on requests to compute or mention a subtraction between values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Anton
    -0.07
     rotating
    -0.07
     Salmon
    -0.06
     om
    -0.06
    ps
    -0.06
    sw
    -0.06
    Node
    -0.06
    .ru
    -0.06
    Bot
    -0.06
     Manor
    -0.06
    POSITIVE LOGITS
    replaceAll
    0.07
     handleMessage
    0.07
     discontin
    0.07
    YPRE
    0.07
     difference
    0.07
     Difference
    0.07
    mind
    0.06
    ythe
    0.06
    "value
    0.06
    battle
    0.06
    Act Density 0.007%

    No Known Activations