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

    Neuronpedia

    INDEX
    Explanations

    question marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Land
    -0.07
     flavor
    -0.07
     drawable
    -0.06
     pudding
    -0.06
     ROAD
    -0.06
     Alaska
    -0.06
    Bindings
    -0.06
    American
    -0.06
    menu
    -0.06
    ครง
    -0.06
    POSITIVE LOGITS
    審
    0.07
    ас
    0.07
     rencont
    0.07
    ~-~-
    0.07
     résult
    0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
     /><
    0.06
     QTest
    0.06
     ماند
    0.06
    ?’
    0.06
    Act Density 0.086%

    No Known Activations