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

    Neuronpedia

    INDEX
    Explanations

    further detail

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     **/
    0.40
    බ
    0.40
    ↵
    0.39
     विक
    0.38
     avg
    0.37
     редак
    0.36
     parsley
    0.36
     *$
    0.36
     sáb
    0.35
    不太
    0.35
    POSITIVE LOGITS
    accep
    0.38
     parameter
    0.38
     રહ્યું
    0.38
    inous
    0.37
    alur
    0.37
    aldi
    0.37
    ats
    0.36
    arle
    0.36
    زیز
    0.35
    ungnya
    0.35
    Act Density 0.000%

    No Known Activations