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
     kaufen
    -0.08
     spp
    -0.07
     Thema
    -0.07
    .getInfo
    -0.07
    这只
    -0.07
    (fullfile
    -0.07
     malaysia
    -0.07
     bụng
    -0.07
    优于
    -0.07
    ingo
    -0.07
    POSITIVE LOGITS
     returns
    0.08
    -stream
    0.07
    ◚
    0.07
    進
    0.07
     �
    0.07
     determined
    0.06
     автор
    0.06
    .display
    0.06
    ]');↵
    0.06
     الج
    0.06
    Act Density 0.002%

    No Known Activations