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

    Neuronpedia

    INDEX
    Explanations

    code configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olders
    -0.07
    lando
    -0.07
     ------
    -0.06
     divergence
    -0.06
     yetiş
    -0.06
    ffen
    -0.06
     amber
    -0.06
     binh
    -0.06
    (light
    -0.06
     labyrinth
    -0.06
    POSITIVE LOGITS
    اي
    0.07
    pixels
    0.07
     ridiculously
    0.06
    ,pos
    0.06
     banana
    0.06
    руг
    0.06
    evaluation
    0.06
    tap
    0.06
     พ
    0.06
    	resolve
    0.06
    Act Density 0.003%

    No Known Activations