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

    Neuronpedia

    INDEX
    Explanations

    Non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vomiting
    -0.07
     demonstrates
    -0.07
     commas
    -0.07
     delegated
    -0.07
     WORD
    -0.07
     GRAPH
    -0.07
     rains
    -0.07
    	step
    -0.07
     stools
    -0.07
     walked
    -0.07
    POSITIVE LOGITS
     local
    0.07
    صدي
    0.07
     particul
    0.07
    仔
    0.07
    �
    0.06
    соедин
    0.06
    ثور
    0.06
     sewer
    0.06
    .twitch
    0.06
    арам
    0.06
    Act Density 0.014%

    No Known Activations