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

    Neuronpedia

    INDEX
    Explanations

    modular arithmetic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     понимаю
    -0.08
     xxxx
    -0.07
     забот
    -0.07
    -0.07
     merged
    -0.07
     podcast
    -0.07
     Pointe
    -0.07
     решила
    -0.07
     rez
    -0.07
    ाख
    -0.07
    POSITIVE LOGITS
     नेपालको
    0.09
     افغانستان
    0.08
     antif
    0.08
     ugy
    0.08
    akc
    0.08
    xor
    0.08
    hurt
    0.08
    .inv
    0.08
    fruit
    0.08
     recipro
    0.08
    Act Density 0.021%
    No Known Activations