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

    Neuronpedia

    INDEX
    Explanations

    Video playback controls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bart
    -0.08
    相当
    -0.07
     Row
    -0.07
     Plenty
    -0.06
     bunun
    -0.06
    ion
    -0.06
     Bath
    -0.06
     справи
    -0.06
     entropy
    -0.06
    _counter
    -0.06
    POSITIVE LOGITS
     flags
    0.06
    	cv
    0.06
    ":"/
    0.06
     Chevrolet
    0.06
     Worldwide
    0.06
    หลด
    0.06
    :end
    0.06
    Unexpected
    0.06
    agi
    0.06
    _ic
    0.06
    Act Density 0.009%

    No Known Activations