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

    Neuronpedia

    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    免税
    -0.07
    スーパ
    -0.06
    amin
    -0.06
    נדר
    -0.06
    综合体
    -0.06
    湖南省
    -0.06
    Reducer
    -0.06
    Pic
    -0.06
    IGNAL
    -0.06
    _sw
    -0.06
    POSITIVE LOGITS
    FormatException
    0.07
    회의
    0.07
    leared
    0.07
    TASK
    0.07
    logic
    0.07
    _HEX
    0.07
    (Throwable
    0.06
    gle
    0.06
    .FileReader
    0.06
    _AI
    0.06
    Act Density 0.032%

    No Known Activations