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

    Neuronpedia

    INDEX
    Explanations

    //

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     عص
    -0.07
    .”↵↵
    -0.06
     �
    -0.06
     Duo
    -0.06
     skinny
    -0.06
    續
    -0.06
    .LinearLayoutManager
    -0.06
    =User
    -0.06
     �
    -0.06
     ।↵
    -0.06
    POSITIVE LOGITS
     repairs
    0.07
     clang
    0.06
    pra
    0.06
    ////////////////////////////////////////////////////////////////////////////////
    0.06
    vis
    0.06
     laps
    0.06
    /response
    0.06
    utive
    0.06
     recovered
    0.06
    (formatter
    0.06
    Act Density 0.004%

    No Known Activations