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

    Neuronpedia

    INDEX
    Explanations

    which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yacht
    -0.06
     Herc
    -0.06
     ruta
    -0.06
    flate
    -0.06
    ?>"/>↵
    -0.06
    "
    -0.06
    "G
    -0.06
     Indie
    -0.06
    興
    -0.06
    —for
    -0.06
    POSITIVE LOGITS
     вій
    0.07
     castle
    0.06
     gambling
    0.06
     parchment
    0.06
     Εκ
    0.06
    스는
    0.06
    .Cast
    0.06
    큼
    0.06
    etzt
    0.06
     Trotsky
    0.06
    Act Density 0.001%

    No Known Activations