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

    Neuronpedia

    INDEX
    Explanations

    additives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rad
    -0.07
    richText
    -0.06
    erator
    -0.06
    238
    -0.06
     dout
    -0.06
    etype
    -0.06
     син
    -0.06
    ad
    -0.06
     ست
    -0.06
     Nun
    -0.06
    POSITIVE LOGITS
     Insider
    0.06
     Asheville
    0.06
    StackTrace
    0.06
     fq
    0.06
     retarded
    0.06
     Recovery
    0.06
     aliment
    0.06
     maint
    0.06
    Sometimes
    0.06
     toler
    0.06
    Act Density 0.067%

    No Known Activations