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

    Neuronpedia

    INDEX
    Explanations

    contained herein

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Verwendung
    0.45
    诣
    0.38
    солю
    0.38
    ौड़
    0.38
     വഴി
    0.37
     representado
    0.37
    ወዳ
    0.36
    𝐵
    0.36
     representada
    0.35
     використання
    0.35
    POSITIVE LOGITS
     academia
    0.46
     ,
    0.38
     printer
    0.35
     mats
    0.35
     printers
    0.34
    pad
    0.33
     outlook
    0.33
    ಳೆದ
    0.33
     lob
    0.33
     opening
    0.32
    Act Density 0.002%

    No Known Activations