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

    Neuronpedia

    INDEX
    Explanations

    academic writing/citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     víctima
    -0.08
     pant
    -0.07
     Há
    -0.07
     MSD
    -0.07
     establishments
    -0.07
    PCODE
    -0.07
     respected
    -0.07
     ['$
    -0.07
    ǿ
    -0.07
    곀
    -0.07
    POSITIVE LOGITS
    ret
    0.07
    orem
    0.07
    urette
    0.07
    츰
    0.07
    폅
    0.07
    בהיר
    0.07
    aurant
    0.06
    Elect
    0.06
     reliant
    0.06
    [R
    0.06
    Act Density 0.151%

    No Known Activations