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

    Neuronpedia

    INDEX
    Explanations

    program

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     राजा
    -0.08
     patent
    -0.08
     Aga
    -0.08
     inventions
    -0.08
    ...]
    -0.08
     ارتباط
    -0.08
    istors
    -0.08
     mitochond
    -0.07
     Fingers
    -0.07
    aph
    -0.07
    POSITIVE LOGITS
     duration
    0.11
    Duration
    0.11
    	duration
    0.10
     dauert
    0.10
    /course
    0.10
     Duration
    0.10
    _duration
    0.10
    duration
    0.10
     durations
    0.10
     dauern
    0.09
    Act Density 0.041%

    No Known Activations