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

    Neuronpedia

    INDEX
    Explanations

    relevance and importance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    çi
    -0.08
    /world
    -0.08
     orin
    -0.08
     Conse
    -0.08
    टना
    -0.08
    	world
    -0.08
     tslib
    -0.08
     surprising
    -0.08
    टे
    -0.08
    aub
    -0.08
    POSITIVE LOGITS
     ohnehin
    0.09
     ?
    0.08
     justement
    0.07
     ethos
    0.07
    Deliver
    0.07
     ebenfalls
    0.07
     emphasis
    0.07
    protocol
    0.07
    Protocol
    0.07
     aims
    0.07
    Act Density 0.085%

    No Known Activations