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

    Neuronpedia

    INDEX
    Explanations

    States

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ?>
↵
    -0.09
    遊
    -0.06
    ilee
    -0.06
    ulent
    -0.06
     Deer
    -0.06
     autobi
    -0.06
    exclusive
    -0.06
     compressed
    -0.06
    _raises
    -0.06
    ONO
    -0.06
    POSITIVE LOGITS
    Others
    0.06
    aising
    0.06
     Bolivia
    0.06
    ror
    0.06
    )c
    0.06
     Adoption
    0.06
    having
    0.06
    Had
    0.06
     campaigners
    0.06
    /Images
    0.06
    Act Density 0.043%

    No Known Activations