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

    Neuronpedia

    INDEX
    Explanations

    common words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pastors
    -0.07
     engaging
    -0.07
     enslaved
    -0.07
     نقشه
    -0.06
    债
    -0.06
    총
    -0.06
     permitting
    -0.06
     than
    -0.06
    -high
    -0.06
    -id
    -0.06
    POSITIVE LOGITS
     intake
    0.07
    ]),
    0.06
    =''):↵
    0.06
    -mask
    0.06
     Mineral
    0.06
    teri
    0.06
    .Exit
    0.06
    _Label
    0.06
    ();
    0.06
    items
    0.06
    Act Density 0.067%

    No Known Activations