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

    Neuronpedia

    INDEX
    Explanations

    hotel amenities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     будет
    -0.07
     deemed
    -0.07
    Tesla
    -0.07
     III
    -0.06
     Acts
    -0.06
     clues
    -0.06
    straints
    -0.06
    ัน
    -0.06
    ör
    -0.06
    DEBUG
    -0.06
    POSITIVE LOGITS
     pursuing
    0.06
    احة
    0.06
    Opacity
    0.06
     sectional
    0.06
     ));↵
    0.05
     Sink
    0.05
     Scha
    0.05
     totals
    0.05
    ]));↵
    0.05
     bre
    0.05
    Act Density 0.010%

    No Known Activations