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

    Neuronpedia

    INDEX
    Explanations

    Neutral topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Haj
    -0.08
    借此
    -0.08
    BAT
    -0.08
    .jet
    -0.07
     scrollTo
    -0.07
    ABC
    -0.07
     hät
    -0.07
     giờ
    -0.07
     hl
    -0.07
     {?}
    -0.07
    POSITIVE LOGITS
     Terra
    0.07
    埆
    0.07
     Sacr
    0.07
    떳
    0.07
     Теп
    0.07
    >()↵
    0.06
     reco
    0.06
     الع
    0.06
    岢
    0.06
     fores
    0.06
    Act Density 0.002%

    No Known Activations