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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -da
    -0.07
     DISCLAIM
    -0.07
    ,args
    -0.07
    "Do
    -0.07
    _on
    -0.07
     вним
    -0.06
    spin
    -0.06
     Remed
    -0.06
     echang
    -0.06
     Christoph
    -0.06
    POSITIVE LOGITS
    امي
    0.07
     nominate
    0.06
     softmax
    0.06
    oogle
    0.06
    不要
    0.06
    码
    0.06
    퇴
    0.06
    uly
    0.06
     bad
    0.06
    वर
    0.05
    Act Density 0.022%

    No Known Activations