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

    Neuronpedia

    INDEX
    Explanations

    B

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    went
    -0.07
    不说
    -0.07
    .tip
    -0.07
     Lopez
    -0.07
     shallow
    -0.06
     spokes
    -0.06
    畅
    -0.06
     speaks
    -0.06
     Allocation
    -0.06
     kept
    -0.06
    POSITIVE LOGITS
    _winner
    0.10
     urlpatterns
    0.08
    UTDOWN
    0.07
     CONTENT
    0.07
     ellipt
    0.07
    querySelector
    0.07
    Pose
    0.07
     MATRIX
    0.07
     servings
    0.07
    YPRE
    0.07
    Act Density 0.023%

    No Known Activations