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

    Neuronpedia

    INDEX
    Explanations

    multiple

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'on
    -0.08
    (...)↵
    -0.07
    [in
    -0.07
     appName
    -0.07
     novo
    -0.06
    $model
    -0.06
     warrant
    -0.06
    %;↵
    -0.06
    ся
    -0.06
     μέρος
    -0.06
    POSITIVE LOGITS
    _CHANGE
    0.07
    revision
    0.07
     departing
    0.07
    communications
    0.07
    ureka
    0.06
    extAlignment
    0.06
     кас
    0.06
    .ListBox
    0.06
    forcements
    0.06
     reusable
    0.06
    Act Density 0.004%

    No Known Activations