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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nhau
    -0.07
     vend
    -0.07
     Định
    -0.07
     edu
    -0.07
    ωση
    -0.07
     rosa
    -0.07
     Sanayi
    -0.06
     madrid
    -0.06
    JUnit
    -0.06
     Oscars
    -0.06
    POSITIVE LOGITS
     and
    0.10
     or
    0.09
     amd
    0.07
     AND
    0.06
     flames
    0.06
     struck
    0.06
    EB
    0.06
    AndPassword
    0.06
     použití
    0.06
     und
    0.06
    Act Density 0.065%

    No Known Activations