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

    Neuronpedia

    INDEX
    Explanations

    Mixed languages, "form", format

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     breach
    -0.07
    SingleOrDefault
    -0.07
    安东
    -0.07
    tone
    -0.07
     Enlightenment
    -0.07
    ڪ
    -0.07
    slope
    -0.07
     positivity
    -0.07
    感动
    -0.07
     ambiguous
    -0.07
    POSITIVE LOGITS
     shr
    0.07
    עור
    0.07
    ופן
    0.07
     עכשיו
    0.07
    #define
    0.07
     המי
    0.07
    QRST
    0.07
    יצר
    0.07
    UMAN
    0.07
    -access
    0.06
    Act Density 0.011%

    No Known Activations