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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "];
    -0.07
    _Resource
    -0.06
    ']+
    -0.06
    _net
    -0.06
    fly
    -0.06
    رانی
    -0.06
    Life
    -0.06
     kontrol
    -0.06
    '])
    -0.06
    "],
    -0.06
    POSITIVE LOGITS
     thanh
    0.06
    IRECT
    0.06
     Joined
    0.06
    /ac
    0.06
     bình
    0.06
    rules
    0.06
     соответств
    0.06
    larını
    0.06
     Heroes
    0.06
    /gcc
    0.06
    Act Density 0.400%

    No Known Activations