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

    Neuronpedia

    INDEX
    Explanations

    building

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.91
     Paglinawan
    -0.64
    httphttps
    -0.62
    bewerken
    -0.60
     kaynağından
    -0.59
    nungen
    -0.58
    webElementXpaths
    -0.57
    וויק
    -0.56
    Anmerkungen
    -0.54
    taku
    -0.53
    POSITIVE LOGITS
    TemporalType
    0.50
    ButterKnife
    0.46
    ExtendWith
    0.46
     Laver
    0.44
    chenken
    0.43
     mogen
    0.43
    TestingModule
    0.43
    érience
    0.41
    ETC
    0.41
    (;;)
    0.40
    Act Density 0.037%

    No Known Activations