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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oprav
    -0.07
     negocio
    -0.06
     Giving
    -0.06
    graphs
    -0.06
     Hughes
    -0.06
     تست
    -0.06
     Ad
    -0.06
    TRIES
    -0.06
    icont
    -0.06
    them
    -0.06
    POSITIVE LOGITS
    phins
    0.07
    Tại
    0.07
    Во
    0.06
     Tại
    0.06
    瞬
    0.06
     trapped
    0.06
     aucun
    0.06
     เข
    0.06
    최고
    0.06
     prázd
    0.06
    Act Density 0.002%

    No Known Activations