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

    Neuronpedia

    INDEX
    Explanations

    train stations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Best
    -0.08
    athing
    -0.08
    =options
    -0.08
    (rowIndex
    -0.07
    的最大
    -0.07
    hest
    -0.07
     descricao
    -0.07
    _order
    -0.07
    Textarea
    -0.07
    THEN
    -0.07
    POSITIVE LOGITS
    洛克
    0.07
    .MULT
    0.06
    /downloads
    0.06
    ∂
    0.06
    Vector
    0.06
    アル
    0.06
    BigDecimal
    0.06
    하였다
    0.06
    翷
    0.06
    ออ
    0.06
    Act Density 0.050%

    No Known Activations