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

    Neuronpedia

    INDEX
    Explanations

    What

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     einf
    -0.07
    níků
    -0.07
     Chúng
    -0.06
    arge
    -0.06
    -step
    -0.06
    ifferent
    -0.06
    ijkstra
    -0.06
     disparities
    -0.06
    essel
    -0.06
    	diff
    -0.06
    POSITIVE LOGITS
     Gothic
    0.07
     drying
    0.07
     Trace
    0.06
    acad
    0.06
     inmate
    0.06
    .currentUser
    0.06
     wildfire
    0.06
     adc
    0.06
    _START
    0.06
    tweet
    0.06
    Act Density 0.003%

    No Known Activations