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

    Neuronpedia

    INDEX
    Explanations

    place names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oti
    -0.31
    åIJĮæľŁ
    -0.29
    otive
    -0.26
     Slovakia
    -0.25
    éĽªèĬ±
    -0.25
     fittings
    -0.25
    _OT
    -0.25
     cloudy
    -0.25
    读åIJİ
    -0.25
    碲
    -0.25
    POSITIVE LOGITS
    jure
    0.29
    便
    0.29
    /gcc
    0.28
    issen
    0.27
     trilogy
    0.26
     ourselves
    0.26
    弦
    0.26
     buzz
    0.25
     efficiently
    0.25
    çĽij
    0.25
    Act Density 0.204%

    No Known Activations