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

    Neuronpedia

    INDEX
    Explanations

    stage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _prov
    -0.07
     noon
    -0.07
    burst
    -0.07
     Titles
    -0.06
     […]↵↵
    -0.06
    _CON
    -0.06
     drawbacks
    -0.06
     Admin
    -0.06
    ENSE
    -0.06
    _locator
    -0.06
    POSITIVE LOGITS
    .Transactional
    0.08
    ể
    0.06
    nostic
    0.06
     sic
    0.06
     Lee
    0.06
    иму
    0.06
    (styles
    0.06
     tiền
    0.06
    javascript
    0.06
     mohla
    0.06
    Act Density 0.016%

    No Known Activations