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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -us
    -0.08
     Fool
    -0.07
    eten
    -0.07
     docking
    -0.07
     Continent
    -0.07
     sembl
    -0.07
     Delegate
    -0.06
    ülü
    -0.06
    akes
    -0.06
    asket
    -0.06
    POSITIVE LOGITS
     useSelector
    0.06
     mz
    0.06
    백
    0.06
    (Message
    0.06
     kond
    0.06
    ewhere
    0.06
    =("
    0.06
     cuda
    0.06
     orderby
    0.06
    electron
    0.06
    Act Density 0.007%

    No Known Activations