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

    Neuronpedia

    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >You
    -0.07
     irreversible
    -0.07
    ichever
    -0.07
    Font
    -0.07
    Tickets
    -0.06
    Mean
    -0.06
    리를
    -0.06
     rating
    -0.06
     Subject
    -0.06
    parsers
    -0.06
    POSITIVE LOGITS
    .fa
    0.06
    　　　　 　
    0.06
    iltere
    0.06
    련
    0.06
     PSG
    0.06
     [&
    0.06
     bla
    0.06
    	component
    0.06
    (beta
    0.06
    .card
    0.06
    Act Density 0.016%

    No Known Activations