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

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [edge
    -0.07
    [token
    -0.07
     관한
    -0.06
    �다
    -0.06
     fırsat
    -0.06
     gelir
    -0.06
     tandem
    -0.06
    TEGER
    -0.06
    rahim
    -0.06
     Ihren
    -0.06
    POSITIVE LOGITS
    _conf
    0.07
     required
    0.06
    gb
    0.06
     rentals
    0.06
    (mon
    0.06
    creative
    0.06
    пол
    0.06
     table
    0.06
    UTF
    0.06
     provincia
    0.06
    Act Density 0.075%

    No Known Activations