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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eat
    -0.06
     �
    -0.06
     calendars
    -0.06
    奇
    -0.06
     Air
    -0.06
     conducive
    -0.06
    �
    -0.06
     ταιν
    -0.06
    .words
    -0.06
     transformer
    -0.06
    POSITIVE LOGITS
    271
    0.08
    MENTS
    0.07
     Milano
    0.07
    -che
    0.06
     multiplying
    0.06
    ált
    0.06
    �
    0.06
    05
    0.06
    psz
    0.06
    PreparedStatement
    0.06
    Act Density 0.075%

    No Known Activations