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

    Neuronpedia

    INDEX
    Explanations

    same

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    illin
    -0.28
    ####↵
    -0.27
    çĶŁäº§çļĦ
    -0.26
    eming
    -0.26
    åĬĽè¿ĺæĺ¯
    -0.25
    arian
    -0.25
    ivent
    -0.24
    uitar
    -0.24
    æľīéĴĪ对æĢ§
    -0.24
    sWith
    -0.24
    POSITIVE LOGITS
     snd
    0.27
    erd
    0.26
    _soup
    0.26
    .wav
    0.25
    oft
    0.24
    ick
    0.24
    裳
    0.24
    _UT
    0.24
    æĹ©æĻļ
    0.24
     Irvine
    0.23
    Act Density 0.009%

    No Known Activations