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

    Neuronpedia

    INDEX
    Explanations

    Illegal activity and censorship

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Radius
    -0.07
     petits
    -0.07
     initiator
    -0.06
    	day
    -0.06
     tavern
    -0.06
     theology
    -0.06
    uala
    -0.06
     limited
    -0.06
    departments
    -0.06
    choice
    -0.06
    POSITIVE LOGITS
    arParams
    0.07
    ğit
    0.07
    rix
    0.07
    унок
    0.07
     ******************************************************************************/↵↵
    0.06
    вещ
    0.06
    	W
    0.06
    _slug
    0.06
     Lord
    0.06
    帝
    0.06
    Act Density 0.018%

    No Known Activations