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

    Neuronpedia

    INDEX
    Explanations

    devices and downloads

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Number
    -0.07
     three
    -0.07
    .Toast
    -0.07
     Minister
    -0.07
    (element
    -0.07
     Green
    -0.07
    _USERNAME
    -0.07
     president
    -0.07
    .MESSAGE
    -0.06
    ῑ
    -0.06
    POSITIVE LOGITS
    ヱ
    0.07
    orta
    0.06
    primer
    0.06
    heap
    0.06
     réfé
    0.06
     artifacts
    0.06
    caled
    0.06
    broker
    0.06
    镌
    0.06
     timestamps
    0.06
    Act Density 0.001%

    No Known Activations