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

    Neuronpedia

    INDEX
    Explanations

    grammar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    828
    -0.07
     Laws
    -0.07
    оля
    -0.07
    IEEE
    -0.06
    356
    -0.06
    means
    -0.06
    via
    -0.06
    ici
    -0.06
    νονται
    -0.06
    敷
    -0.06
    POSITIVE LOGITS
    ):(
    0.07
     к
    0.07
    lif
    0.07
     HI
    0.07
     bishop
    0.06
    .Group
    0.06
    >(*
    0.06
    .pan
    0.06
     Exhibit
    0.06
    .';↵
    0.06
    Act Density 0.050%

    No Known Activations