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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ंड
    -0.07
     Payment
    -0.07
     management
    -0.07
     Mapping
    -0.07
     excluded
    -0.06
     Comics
    -0.06
    Thêm
    -0.06
     trusted
    -0.06
     KK
    -0.06
     Mint
    -0.06
    POSITIVE LOGITS
    mqtt
    0.08
    _classes
    0.07
    classpath
    0.06
     being
    0.06
    .BLUE
    0.06
    .pass
    0.06
    .zeros
    0.06
    irth
    0.06
     목록
    0.06
    .pol
    0.06
    Act Density 0.110%

    No Known Activations