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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    merchant
    -0.08
    	Write
    -0.08
     省
    -0.07
    Clause
    -0.07
    -validation
    -0.07
    Transaction
    -0.07
    开发
    -0.07
     municipalities
    -0.07
     врач
    -0.07
    USART
    -0.07
    POSITIVE LOGITS
     beim
    0.07
     Are
    0.06
    aleb
    0.06
    curl
    0.06
    .El
    0.06
     werden
    0.06
     stems
    0.06
     knows
    0.06
     Uncle
    0.06
     waive
    0.06
    Act Density 0.032%

    No Known Activations