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

    Neuronpedia

    INDEX
    Explanations

    What

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     helpful
    -0.07
     marker
    -0.07
     Canada
    -0.06
     Kushner
    -0.06
    asuring
    -0.06
     -------------------------------------------------------------------------
    -0.06
     president
    -0.06
    assemble
    -0.06
    .RadioButton
    -0.06
    Scalar
    -0.06
    POSITIVE LOGITS
     assortment
    0.07
     Alzheimer
    0.06
    rol
    0.06
     gorge
    0.06
    814
    0.06
     RSVP
    0.06
     Vie
    0.06
     what
    0.06
    ียง
    0.06
    _BL
    0.06
    Act Density 0.021%

    No Known Activations