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

    Neuronpedia

    INDEX
    Explanations

    message

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abil
    -0.27
     pac
    -0.24
    jak
    -0.24
    arov
    -0.23
     uns
    -0.23
     riv
    -0.23
    æĬ¢
    -0.23
     ê·¸ëŁ°
    -0.23
    é»ĺé»ĺåľ°
    -0.23
    è¡¥é½IJ
    -0.23
    POSITIVE LOGITS
    iliate
    0.27
    椴
    0.27
    æĻĴ
    0.26
    ampler
    0.26
    dress
    0.25
    leine
    0.24
     Born
    0.24
     eux
    0.24
    ound
    0.23
    /cop
    0.23
    Act Density 0.030%

    No Known Activations