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

    Neuronpedia

    INDEX
    Explanations

    speed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    委员会
    -0.07
     implement
    -0.07
    -wage
    -0.07
    ��
    -0.06
     torture
    -0.06
    Tracks
    -0.06
     expres
    -0.06
     userAgent
    -0.06
    _notifications
    -0.06
     свя
    -0.06
    POSITIVE LOGITS
     швид
    0.07
     alerted
    0.07
     없는
    0.06
    IVO
    0.06
     IMPORTANT
    0.06
    (abs
    0.06
    	rows
    0.06
    atsby
    0.06
     Order
    0.06
     />
    0.06
    Act Density 0.027%

    No Known Activations