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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ')).
    -0.07
    umeric
    -0.07
     ['.
    -0.06
     ethers
    -0.06
    _PRINTF
    -0.06
     stringBy
    -0.06
    iere
    -0.06
    游
    -0.06
    >();↵
    -0.06
    ");
    -0.06
    POSITIVE LOGITS
    lb
    0.07
     метод
    0.07
     SPD
    0.06
     civilians
    0.06
     збір
    0.06
    ınd
    0.06
    iki
    0.06
    udp
    0.06
    ستگی
    0.06
    保障
    0.06
    Act Density 0.047%

    No Known Activations