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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tmp
    -0.07
    巧
    -0.07
     Ronaldo
    -0.06
     powder
    -0.06
    ILD
    -0.06
    ्ब
    -0.06
     sống
    -0.06
    iks
    -0.06
    óc
    -0.06
    Ot
    -0.06
    POSITIVE LOGITS
     questi
    0.07
    _start
    0.07
    ismatic
    0.07
    ştir
    0.06
     Bitcoins
    0.06
    (Tile
    0.06
    _cores
    0.06
     ngăn
    0.06
     ignore
    0.06
    -exp
    0.06
    Act Density 0.029%

    No Known Activations