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

    Neuronpedia

    INDEX
    Explanations

    large groups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _heap
    -0.07
     Ratio
    -0.07
    Men
    -0.07
    Raised
    -0.07
     vyšší
    -0.07
     richTextBox
    -0.07
    Women
    -0.06
    �
    -0.06
     predicting
    -0.06
     zoning
    -0.06
    POSITIVE LOGITS
    ADDR
    0.07
     DOES
    0.06
    ANGES
    0.06
    (Rect
    0.06
    .ActionBar
    0.06
    された
    0.06
     negatives
    0.06
    нув
    0.06
     مج
    0.06
    @foreach
    0.06
    Act Density 0.257%

    No Known Activations