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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ｳ
    -0.08
     Hòa
    -0.08
    [V
    -0.07
    WIDTH
    -0.07
    英文
    -0.07
     GO
    -0.07
     crowded
    -0.06
    ㋯
    -0.06
    独
    -0.06
     wp
    -0.06
    POSITIVE LOGITS
     Fet
    0.08
    .signature
    0.07
    _receipt
    0.07
    ast
    0.07
    涑
    0.07
    琏
    0.07
     وغير
    0.07
    .cart
    0.07
    ductive
    0.07
    淯
    0.07
    Act Density 0.051%

    No Known Activations