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

    Neuronpedia

    INDEX
    Explanations

    Time frequency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mag
    -0.07
     Ginger
    -0.06
    _inv
    -0.06
    25
    -0.06
    uite
    -0.06
    _before
    -0.06
     sales
    -0.06
    276
    -0.06
     goose
    -0.06
     hackers
    -0.06
    POSITIVE LOGITS
    irie
    0.07
    church
    0.06
     phù
    0.06
     enquiry
    0.06
    #index
    0.06
    ).\
    0.06
    нів
    0.06
    反
    0.06
    Control
    0.06
    ergarten
    0.06
    Act Density 0.038%

    No Known Activations