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

    Neuronpedia

    INDEX
    Explanations

    promotion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _trees
    -0.07
    ubb
    -0.06
    []{
    -0.06
     nhỏ
    -0.06
    ्क
    -0.06
    719
    -0.06
     meter
    -0.06
     IL
    -0.06
     Threshold
    -0.06
     inhal
    -0.06
    POSITIVE LOGITS
     HARD
    0.07
     creampie
    0.07
    이나
    0.06
     crafting
    0.06
    stellar
    0.06
    createCommand
    0.06
    (MouseEvent
    0.06
     �
    0.06
    vrolet
    0.06
    สภ
    0.06
    Act Density 0.002%

    No Known Activations