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

    Neuronpedia

    INDEX
    Explanations

    Text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Chain
    -0.07
    CMD
    -0.07
    (avg
    -0.07
     司
    -0.06
    }',
    -0.06
    .addr
    -0.06
     waypoint
    -0.06
    	swap
    -0.06
     angular
    -0.06
    macen
    -0.06
    POSITIVE LOGITS
     Reports
    0.07
     jaké
    0.06
    More
    0.06
     Stard
    0.06
    ics
    0.06
    						↵
    0.06
    状况
    0.06
     تع
    0.06
     आपक
    0.06
     tuned
    0.06
    Act Density 0.000%

    No Known Activations