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

    Neuronpedia

    INDEX
    Explanations

    st

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .same
    -0.08
     Ann
    -0.07
    (sorted
    -0.07
     Panel
    -0.07
     �
    -0.07
     Alameda
    -0.07
     Through
    -0.07
     Ladies
    -0.07
     thanh
    -0.07
     Як
    -0.07
    POSITIVE LOGITS
    unka
    0.09
    Historical
    0.09
     century
    0.09
     છેલ્લા
    0.08
     folkl
    0.08
    обрет
    0.08
     historical
    0.08
     historischen
    0.08
    -century
    0.08
     Jahrhund
    0.08
    Act Density 0.002%

    No Known Activations