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

    Neuronpedia

    INDEX
    Explanations

    tasks and participants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     concession
    -0.07
     ngành
    -0.07
     ucwords
    -0.06
    Console
    -0.06
    	The
    -0.06
     encompasses
    -0.06
    μφ
    -0.06
     завд
    -0.06
     Lyons
    -0.06
    managed
    -0.06
    POSITIVE LOGITS
     achieves
    0.07
    езультат
    0.06
    тон
    0.06
    (edge
    0.06
     значит
    0.06
    .modified
    0.06
     Ellison
    0.06
    .Format
    0.06
    discard
    0.06
     голову
    0.06
    Act Density 0.223%

    No Known Activations