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

    Neuronpedia

    INDEX
    Explanations

    neural network adversarial attacks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fr
    -0.08
     Suppliers
    -0.07
    reffen
    -0.07
     Tou
    -0.07
    dataGridView
    -0.07
    isoft
    -0.07
    _fin
    -0.07
    DN
    -0.07
     마
    -0.07
     ending
    -0.07
    POSITIVE LOGITS
    (rest
    0.07
     oraz
    0.07
    oric
    0.07
    ()})↵
    0.07
     зарегист
    0.06
    *:
    0.06
     Front
    0.06
     (...
    0.06
    긋
    0.06
    ('@/
    0.06
    Act Density 0.039%

    No Known Activations