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

    Neuronpedia

    INDEX
    Explanations

    Addressing or instructing "you"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     raised
    -0.06
     Pakistan
    -0.06
     Chairs
    -0.06
    >&
    -0.06
    Barrier
    -0.06
     ев
    -0.06
    рик
    -0.06
     CDs
    -0.06
    ียนร
    -0.06
     prior
    -0.06
    POSITIVE LOGITS
     перек
    0.06
     ').
    0.06
     `{
    0.06
    SACTION
    0.06
    .isfile
    0.06
    Arg
    0.06
    \Desktop
    0.06
    ::{
    0.06
     '%$
    0.06
    √
    0.06
    Act Density 0.102%

    No Known Activations