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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     into
    -0.07
     T
    -0.07
     Vert
    -0.07
    utters
    -0.07
     over
    -0.07
     subdivision
    -0.07
     PIB
    -0.07
     division
    -0.07
     interaction
    -0.07
     Tub
    -0.07
    POSITIVE LOGITS
     healthiest
    0.10
     самый
    0.09
    ermission
    0.09
     തന്നെ
    0.09
    lowest
    0.09
     headphone
    0.09
    Largest
    0.08
    Discard
    0.08
    *)((
    0.08
    !).
    0.08
    Act Density 0.016%

    No Known Activations