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

    Neuronpedia

    INDEX
    Explanations

    question mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dane
    -0.07
     cz
    -0.07
     condu
    -0.07
     ---↵
    -0.06
     Sommer
    -0.06
     نخست
    -0.06
     Dunk
    -0.06
     Nie
    -0.06
     ())↵
    -0.06
    _slices
    -0.06
    POSITIVE LOGITS
    _art
    0.07
     syst
    0.07
    656
    0.07
     Suffolk
    0.06
    στρο
    0.06
    serv
    0.06
     survives
    0.06
     brewers
    0.06
    ۱۹
    0.06
    _press
    0.06
    Act Density 0.009%

    No Known Activations