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

    Neuronpedia

    INDEX
    Explanations

    races

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     separ
    -0.07
     Saint
    -0.07
     yards
    -0.07
    標準
    -0.07
     Bracket
    -0.07
     Ottoman
    -0.07
     sâu
    -0.07
     café
    -0.06
     privat
    -0.06
     fé
    -0.06
    POSITIVE LOGITS
    itle
    0.06
     archived
    0.06
    autos
    0.06
    _rent
    0.06
    け
    0.06
     //
↵
    0.06
    レイ
    0.06
    raises
    0.06
    ;s
    0.06
    `;
    0.06
    Act Density 0.001%

    No Known Activations