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

    Neuronpedia

    INDEX
    Explanations

    code and XML schemas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    概
    -0.07
    ritz
    -0.06
     Québec
    -0.06
    -head
    -0.06
    .PR
    -0.06
    кості
    -0.06
    ्व
    -0.06
    ΑΝΤ
    -0.06
     NR
    -0.06
    чит
    -0.06
    POSITIVE LOGITS
     listings
    0.07
    converted
    0.06
     večer
    0.06
    	boolean
    0.06
     {$
    0.06
     Moved
    0.06
     loneliness
    0.06
    zee
    0.06
     Drinking
    0.06
    $tmp
    0.06
    Act Density 0.022%

    No Known Activations