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
    ologue
    -0.07
    __.
    -0.07
    Cb
    -0.07
    _fname
    -0.07
    局
    -0.07
    bles
    -0.07
    ///<
    -0.07
    .middleware
    -0.07
    _sn
    -0.06
    endid
    -0.06
    POSITIVE LOGITS
    /*↵
    0.08
     Hey
    0.07
    Authorization
    0.07
    .Map
    0.07
     Bark
    0.06
     хто
    0.06
     Lind
    0.06
     Okay
    0.06
     bark
    0.06
     /*↵
    0.06
    Act Density 0.002%

    No Known Activations