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

    Neuronpedia

    INDEX
    Explanations

    only just

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rack
    -0.07
     reput
    -0.07
    ipe
    -0.07
     replen
    -0.06
     кра
    -0.06
     towel
    -0.06
    hole
    -0.06
     zus
    -0.06
    кта
    -0.06
    pipes
    -0.06
    POSITIVE LOGITS
     FG
    0.07
     klid
    0.07
     Newest
    0.07
     republic
    0.06
    /server
    0.06
    (startTime
    0.06
     �
    0.06
    _EXPORT
    0.06
     coverage
    0.06
     **/↵↵
    0.06
    Act Density 0.014%

    No Known Activations