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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bras
    -0.07
    保健
    -0.07
     hàng
    -0.07
    UPLE
    -0.07
    례
    -0.07
     next
    -0.07
     IB
    -0.07
     valeurs
    -0.06
    趋势
    -0.06
    🦄
    -0.06
    POSITIVE LOGITS
    opot
    0.08
    lagen
    0.08
    动人
    0.07
    _correction
    0.07
    .attach
    0.07
    รง
    0.07
    ducible
    0.07
    cheiden
    0.07
     그리스
    0.07
     источ
    0.07
    Act Density 0.003%

    No Known Activations