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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Collider
    -0.07
    duğu
    -0.07
     yPos
    -0.07
    اقة
    -0.06
    istry
    -0.06
     YORK
    -0.06
     enumerate
    -0.06
    .strptime
    -0.06
     '../../../../
    -0.06
    .reshape
    -0.06
    POSITIVE LOGITS
     intimate
    0.07
    RAND
    0.06
     encompass
    0.06
    rays
    0.06
    odeled
    0.06
    went
    0.06
     perpet
    0.06
    Letter
    0.06
     Silent
    0.06
    _ABORT
    0.06
    Act Density 0.024%

    No Known Activations