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

    Neuronpedia

    INDEX
    Explanations

    क

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [p
    -0.07
    -begin
    -0.07
    glob
    -0.07
    387
    -0.06
    тою
    -0.06
    _EVAL
    -0.06
    xdf
    -0.06
    scp
    -0.06
     GDPR
    -0.06
    ț
    -0.06
    POSITIVE LOGITS
     troublesome
    0.07
     corpo
    0.06
     '.')
    0.06
     Sofa
    0.06
    าการ
    0.06
     </>↵
    0.06
    iště
    0.06
    curacy
    0.06
     iNdEx
    0.06
    >>()
    0.06
    Act Density 0.002%

    No Known Activations