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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    렉
    -0.07
     rotten
    -0.07
    -The
    -0.07
     appar
    -0.07
     submar
    -0.06
     Stub
    -0.06
     Craw
    -0.06
     �
    -0.06
     sparse
    -0.06
    変わ
    -0.06
    POSITIVE LOGITS
     readdir
    0.07
     commerc
    0.07
    !
    0.06
    .coordinates
    0.06
    成人
    0.06
     अव
    0.06
     Errors
    0.06
     ↵ ↵
    0.06
    ELL
    0.06
    --
↵
    0.06
    Act Density 0.000%

    No Known Activations