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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Damien
    -0.09
     �
    -0.08
     agar
    -0.08
     Vaughan
    -0.08
    添
    -0.08
    聚
    -0.07
    �
    -0.07
    圈
    -0.07
     упраж
    -0.07
     giải
    -0.07
    POSITIVE LOGITS
     Moss
    0.07
     Blank
    0.07
     കഴ
    0.07
    ๋
    0.07
    larg
    0.07
     આવ
    0.07
     roca
    0.07
     fo
    0.07
     ક
    0.07
     Mer
    0.07
    Act Density 0.059%

    No Known Activations