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

    Neuronpedia

    INDEX
    Explanations

    Video script with graphics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     washers
    -0.09
    协
    -0.08
    Allocation
    -0.07
    _MARK
    -0.07
     ceremonies
    -0.07
    -0.07
     counsel
    -0.07
     cutters
    -0.07
     préserver
    -0.07
    ිය
    -0.07
    POSITIVE LOGITS
     Minh
    0.08
     prominently
    0.08
    თან
    0.08
     verschijnt
    0.08
     Heim
    0.08
     nes
    0.08
     spotlight
    0.08
     Beng
    0.07
    亮
    0.07
    artige
    0.07
    Act Density 0.021%
    No Known Activations