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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     möchten
    -0.07
    evaluate
    -0.07
    contained
    -0.06
    ‌است
    -0.06
     membership
    -0.06
     Depression
    -0.06
     тоді
    -0.06
     srand
    -0.06
    ตอบ
    -0.06
     condition
    -0.06
    POSITIVE LOGITS
     SEL
    0.07
     ATL
    0.07
    BitConverter
    0.07
     Mata
    0.06
    .Asset
    0.06
    Wire
    0.06
     Pasta
    0.06
    .Standard
    0.06
    MatrixXd
    0.06
    Slots
    0.06
    Act Density 0.005%

    No Known Activations