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

    Neuronpedia

    INDEX
    Explanations

    lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     whitespace
    -0.06
    ?>
    -0.06
    nictvím
    -0.06
    .destination
    -0.06
     通
    -0.06
    شتر
    -0.06
    orris
    -0.06
    만원입니다
    -0.06
     تو
    -0.06
     आम
    -0.06
    POSITIVE LOGITS
    Ga
    0.07
    九
    0.07
     Herman
    0.06
    Msg
    0.06
    Added
    0.06
     guaranteed
    0.06
    .copyOf
    0.06
     Jak
    0.06
     Měst
    0.06
     정치
    0.06
    Act Density 0.014%

    No Known Activations