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

    Neuronpedia

    INDEX
    Explanations

    Code with return

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    əsinə
    -0.08
     formulation
    -0.07
     squander
    -0.07
     est
    -0.07
     vocation
    -0.07
    拓
    -0.07
     pursuit
    -0.07
    <float
    -0.07
    .Anchor
    -0.07
    -intensive
    -0.07
    POSITIVE LOGITS
    _mock
    0.15
    mock
    0.15
    	mock
    0.15
    Mock
    0.13
     Mock
    0.13
     mock
    0.13
    (mock
    0.13
     pretending
    0.13
     giả
    0.12
    (Mock
    0.12
    Act Density 0.005%

    No Known Activations