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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (datas
    -0.07
     principalmente
    -0.07
    (site
    -0.07
    .swift
    -0.07
     contradict
    -0.06
    ogi
    -0.06
    	BIT
    -0.06
    Raised
    -0.06
    xfff
    -0.06
     countries
    -0.06
    POSITIVE LOGITS
     Bags
    0.07
    -gnu
    0.06
     maneu
    0.06
    assage
    0.06
    %"
    0.06
     endTime
    0.06
    /how
    0.06
     Kay
    0.06
    det
    0.06
    ์
    0.06
    Act Density 0.010%

    No Known Activations