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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    оты
    -0.07
    ADE
    -0.06
    ele
    -0.06
     Wilkinson
    -0.06
    unde
    -0.06
     superhero
    -0.06
    Polit
    -0.06
    ору
    -0.06
    ).'
    -0.06
    oter
    -0.05
    POSITIVE LOGITS
     EB
    0.07
     συμμε
    0.07
     rallying
    0.07
    Viewport
    0.07
    _FILENAME
    0.07
    .Measure
    0.06
     Rainbow
    0.06
    (Game
    0.06
     logged
    0.06
    (stack
    0.06
    Act Density 0.002%

    No Known Activations