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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tee
    -0.08
    ul
    -0.07
    針
    -0.07
     Bris
    -0.07
     Begin
    -0.07
     start
    -0.07
     suspicious
    -0.07
     confirm
    -0.07
    Depth
    -0.07
     nex
    -0.07
    POSITIVE LOGITS
    ⇙
    0.09
     WWII
    0.07
    _KEYWORD
    0.07
    䗛
    0.07
    Tomorrow
    0.07
    mAh
    0.07
     JComboBox
    0.07
     miłości
    0.07
    っき
    0.07
     Körper
    0.07
    Act Density 0.003%

    No Known Activations