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

    Neuronpedia

    INDEX
    Explanations

    law enforcement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     punishments
    -0.07
    ific
    -0.07
     movers
    -0.07
     SUN
    -0.07
     hoạt
    -0.07
    ilig
    -0.07
     temperatures
    -0.06
    .edu
    -0.06
    	public
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     kurum
    0.07
     SQ
    0.06
    igslist
    0.06
    (""
    0.06
    Iter
    0.06
     exert
    0.06
     wrong
    0.06
    .ss
    0.06
    .MIN
    0.06
    ness
    0.06
    Act Density 0.081%

    No Known Activations