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

    Neuronpedia

    INDEX
    Explanations

    favorites or bookmarks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Majority
    -0.07
    Repeated
    -0.06
    Calibri
    -0.06
     Innov
    -0.06
    गर
    -0.06
    「
    -0.06
     involves
    -0.06
    eki
    -0.06
     Trials
    -0.06
     usefulness
    -0.06
    POSITIVE LOGITS
     expulsion
    0.07
     cumshot
    0.07
     solder
    0.06
     dashed
    0.06
    LK
    0.06
     lends
    0.06
     insure
    0.06
    oden
    0.06
    primitive
    0.06
     erad
    0.06
    Act Density 0.046%

    No Known Activations