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

    Neuronpedia

    INDEX
    Explanations

    math notations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     youthful
    -0.09
     mł
    -0.08
    бек
    -0.08
    (callback
    -0.08
     notes
    -0.07
     backs
    -0.07
    Connect
    -0.07
    (notes
    -0.07
    (results
    -0.07
    	callback
    -0.07
    POSITIVE LOGITS
     Manhattan
    0.12
     ||
    0.09
    ||
    0.09
     rectangular
    0.09
     movement
    0.09
     projecting
    0.09
     traslado
    0.08
    rectangle
    0.08
    hattan
    0.08
    Movement
    0.08
    Act Density 0.008%

    No Known Activations