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

    Neuronpedia

    INDEX
    Explanations

    integer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Premiership
    -0.06
    िनट
    -0.06
     thugs
    -0.06
     Harry
    -0.06
     kaldı
    -0.06
     linkage
    -0.06
    onna
    -0.06
     outset
    -0.06
     STUD
    -0.06
     OrderedDict
    -0.06
    POSITIVE LOGITS
    (Exception
    0.07
     छ
    0.07
     mức
    0.06
     ویکی
    0.06
     eradicate
    0.06
    임
    0.06
     mx
    0.06
    usan
    0.06
     fint
    0.06
    cdot
    0.06
    Act Density 0.006%

    No Known Activations