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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     <!--[
    -0.06
     Friedman
    -0.06
     конце
    -0.06
     Bam
    -0.06
     schw
    -0.06
     분
    -0.06
    versions
    -0.06
     ;)↵↵
    -0.06
     cil
    -0.06
    Green
    -0.06
    POSITIVE LOGITS
    eck
    0.06
     ylabel
    0.06
     khiến
    0.06
    (rank
    0.06
    berries
    0.05
     jeg
    0.05
    ευ
    0.05
    ardown
    0.05
    原来
    0.05
     lái
    0.05
    Act Density 0.004%

    No Known Activations