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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric expressions—figures, percentages, money amounts, dates, and other number tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	act
    -0.07
    Got
    -0.06
    یط
    -0.06
     ugl
    -0.06
    TRIES
    -0.06
     isAuthenticated
    -0.06
    .mov
    -0.06
    ("\"
    -0.06
     getNext
    -0.06
    ，从
    -0.06
    POSITIVE LOGITS
    qui
    0.07
    nesení
    0.07
     عقد
    0.07
    .Pe
    0.06
    HasColumnName
    0.06
    今天
    0.06
     nothing
    0.06
    Không
    0.06
    лены
    0.06
    terra
    0.06
    Act Density 0.027%

    No Known Activations