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

    Neuronpedia

    INDEX
    Explanations

    source code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ingin
    -0.07
     Rush
    -0.07
     bel
    -0.07
    ंज
    -0.06
     경제
    -0.06
     primes
    -0.06
    friend
    -0.06
    (b
    -0.06
    Fault
    -0.06
    alleng
    -0.06
    POSITIVE LOGITS
     Com
    0.07
     sentido
    0.07
     możli
    0.07
     conveying
    0.06
     acquainted
    0.06
     valid
    0.06
    の方
    0.06
    ΕΤ
    0.06
    _observer
    0.06
     hồng
    0.06
    Act Density 0.095%

    No Known Activations