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

    Neuronpedia

    INDEX
    Explanations

    Technology risks and threats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (dir
    -0.07
    พบ
    -0.07
    کا
    -0.07
    Increment
    -0.06
    _IRQn
    -0.06
     Arithmetic
    -0.06
     قرار
    -0.06
    ihilation
    -0.06
     در
    -0.06
    _delegate
    -0.06
    POSITIVE LOGITS
     freeing
    0.07
    .viewModel
    0.06
     waged
    0.06
     spawning
    0.06
    .getCode
    0.06
     Fall
    0.06
     aqu
    0.06
     Taipei
    0.06
     harvested
    0.06
    Raise
    0.06
    Act Density 0.024%

    No Known Activations