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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    背面
    -0.07
    ilename
    -0.07
     istediği
    -0.06
    フル
    -0.06
    node
    -0.06
     Jal
    -0.06
     Dan
    -0.06
    Winter
    -0.06
    LE
    -0.06
    .Utc
    -0.06
    POSITIVE LOGITS
    Mayor
    0.07
    ɵ
    0.07
    otyp
    0.07
    ambio
    0.07
    変わ
    0.07
    相识
    0.07
    慬
    0.07
    מבקר
    0.07
    astery
    0.07
    etu
    0.06
    Act Density 0.039%

    No Known Activations