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

    Neuronpedia

    INDEX
    Explanations

    law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     visibly
    -0.06
    zek
    -0.06
     notebook
    -0.06
    typedef
    -0.06
     kotlinx
    -0.06
    <m
    -0.06
     azi
    -0.06
    isiert
    -0.06
     кноп
    -0.06
    EFI
    -0.06
    POSITIVE LOGITS
    -G
    0.08
    -U
    0.07
    .loader
    0.07
     continuation
    0.06
     DETAILS
    0.06
     Soph
    0.06
     law
    0.06
    ραση
    0.06
    +w
    0.06
     liquor
    0.06
    Act Density 0.006%

    No Known Activations