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

    Neuronpedia

    INDEX
    Explanations

    countries/nationalities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    بس
    -0.07
    authenticated
    -0.06
    ?>/
    -0.06
    ि�
    -0.06
    ismus
    -0.06
    _ind
    -0.06
    .detach
    -0.06
     INST
    -0.06
    DataRow
    -0.06
     giới
    -0.06
    POSITIVE LOGITS
     знову
    0.07
     μ
    0.06
     neuro
    0.06
     Ну
    0.06
    лки
    0.06
     živ
    0.06
    али
    0.06
    Но
    0.06
     foam
    0.06
     Booster
    0.06
    Act Density 0.071%

    No Known Activations