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

    Neuronpedia

    INDEX
    Explanations

    computer security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ли
    -0.06
     müş
    -0.06
    amus
    -0.06
    िद
    -0.06
    algorithm
    -0.06
    .master
    -0.06
    /qu
    -0.06
    ++];↵
    -0.06
    spam
    -0.06
     PartialEq
    -0.06
    POSITIVE LOGITS
     LOS
    0.07
     allies
    0.06
    _args
    0.06
     Het
    0.06
    Het
    0.06
    AGE
    0.06
    acs
    0.06
    ایش
    0.06
    GAN
    0.06
     Called
    0.06
    Act Density 0.029%

    No Known Activations