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

    Neuronpedia

    INDEX
    Explanations

    information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    pler
    -0.07
     harness
    -0.07
    לחם
    -0.07
     Comb
    -0.06
     destinationViewController
    -0.06
    �
    -0.06
     exploded
    -0.06
    cales
    -0.06
    berra
    -0.06
    POSITIVE LOGITS
     стиль
    0.08
    רמת
    0.07
    一把
    0.07
     varied
    0.07
    _equalTo
    0.07
    数组
    0.07
    眼科
    0.07
     아주
    0.07
    둿
    0.07
     assorted
    0.06
    Act Density 0.010%

    No Known Activations