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

    Neuronpedia

    INDEX
    Explanations

    court

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zpracování
    -0.07
    phy
    -0.07
     auxiliary
    -0.06
     Watches
    -0.06
    race
    -0.06
     setters
    -0.06
    Rooms
    -0.06
    poz
    -0.06
     Positive
    -0.06
    MPI
    -0.06
    POSITIVE LOGITS
    asn
    0.08
    aciente
    0.07
    看见
    0.07
    呀
    0.06
     dazu
    0.06
    cef
    0.06
    \OptionsResolver
    0.06
     Dis
    0.06
     الدين
    0.06
     acompanh
    0.06
    Act Density 0.016%

    No Known Activations