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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     이해
    -0.07
     ait
    -0.06
     üç
    -0.06
     về
    -0.06
     currents
    -0.06
     you
    -0.06
    lere
    -0.06
    憶
    -0.06
    oni
    -0.06
     свойства
    -0.06
    POSITIVE LOGITS
    uw
    0.07
     correction
    0.07
     Carnegie
    0.06
    =T
    0.06
     sty
    0.06
    <usize
    0.06
     postgres
    0.06
    ...)↵
    0.06
     hlavu
    0.06
    od
    0.06
    Act Density 0.019%

    No Known Activations