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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .same
    -0.06
    .None
    -0.06
    .post
    -0.06
     хто
    -0.06
    .kernel
    -0.06
     även
    -0.06
    키
    -0.06
    (cps
    -0.06
    \Eloquent
    -0.06
     امکان
    -0.06
    POSITIVE LOGITS
     Orientation
    0.07
     TY
    0.07
     نش
    0.07
     Liber
    0.06
     derby
    0.06
     separately
    0.06
     Đầu
    0.06
     náp
    0.06
    Much
    0.06
    /';↵↵
    0.06
    Act Density 0.000%

    No Known Activations