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

    Neuronpedia

    INDEX
    Explanations

    GitHub Actions workflow steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    இரு
    0.45
    Boltzmann
    0.45
     بمعنى
    0.44
    जनन
    0.43
     reclining
    0.41
    鴛
    0.41
    urethane
    0.41
    Кра
    0.41
    嶠
    0.41
     இரு
    0.40
    POSITIVE LOGITS
     Checkout
    0.66
     actions
    0.65
     checkout
    0.64
     action
    0.64
     job
    0.64
     GitHub
    0.64
     ${{
    0.64
    checkout
    0.61
     step
    0.56
    job
    0.56
    Act Density 0.009%

    No Known Activations