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

    Neuronpedia

    INDEX
    Explanations

    Neural network layers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    request
    -0.08
     bfs
    -0.07
     đánh
    -0.07
    顿
    -0.07
    (message
    -0.07
    꽁
    -0.07
    activation
    -0.07
    alive
    -0.07
    addresses
    -0.07
    策划
    -0.07
    POSITIVE LOGITS
    -ion
    0.08
    蜎
    0.07
     glUniform
    0.07
     recently
    0.07
    )"
    0.07
    ór
    0.07
     olmadığ
    0.06
    بريط
    0.06
    الياب
    0.06
     Soy
    0.06
    Act Density 0.001%

    No Known Activations