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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Reusable
    -0.07
     overpower
    -0.06
     흔
    -0.06
     злоч
    -0.06
     simulation
    -0.06
    rying
    -0.06
     AZ
    -0.06
     Icon
    -0.06
    acom
    -0.06
    CREEN
    -0.06
    POSITIVE LOGITS
     ↵↵
    0.07
    templates
    0.07
    ahr
    0.07
     }),↵
    0.06
    )'],↵
    0.06
     oc
    0.06
    inos
    0.06
    »,
    0.06
     |
    0.06
    }],
    0.06
    Act Density 0.000%

    No Known Activations