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

    Neuronpedia

    INDEX
    Explanations

    light interaction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    行程
    -0.08
    (len
    -0.07
     mắc
    -0.07
    大道
    -0.07
    Hack
    -0.07
     mans
    -0.07
    牛肉
    -0.06
    $args
    -0.06
    <DateTime
    -0.06
     GST
    -0.06
    POSITIVE LOGITS
    ¹
    0.07
     TWO
    0.06
     council
    0.06
     escrit
    0.06
     subsidiary
    0.06
     bureau
    0.06
     выход
    0.06
    ixmap
    0.06
    :before
    0.06
    ATFORM
    0.06
    Act Density 0.008%

    No Known Activations