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

    Neuronpedia

    INDEX
    Explanations

    quality construction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     encryption
    -0.07
     moderated
    -0.07
    .diff
    -0.07
    _PAR
    -0.06
     nowrap
    -0.06
     dull
    -0.06
    	pos
    -0.06
     exec
    -0.06
    EMP
    -0.06
    Coll
    -0.06
    POSITIVE LOGITS
    카지노
    0.07
    othermal
    0.07
    ським
    0.07
     счит
    0.06
     contamination
    0.06
    …………………………………………
    0.06
    ании
    0.06
    ського
    0.06
    анию
    0.06
    ainer
    0.06
    Act Density 0.034%

    No Known Activations