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

    Neuronpedia

    INDEX
    Explanations

    generator

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spir
    -0.29
    schlä
    -0.27
    å¤ĩ
    -0.27
    æĻ®éģį
    -0.27
    heels
    -0.27
    &utm
    -0.26
     greens
    -0.26
    Pane
    -0.26
     Spir
    -0.26
    iles
    -0.25
    POSITIVE LOGITS
    æľīæĦı
    0.28
    åĪĽä¸ļèĢħ
    0.27
    uctive
    0.27
    |[
    0.27
     bulletin
    0.27
    çĽĬ
    0.26
    imest
    0.26
    ucer
    0.26
     stuffing
    0.26
    æ¯Ľ
    0.26
    Act Density 0.034%

    No Known Activations