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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .REQUEST
    -0.08
    comment
    -0.07
    全国人民
    -0.07
    .bool
    -0.07
    -script
    -0.07
     OFF
    -0.07
     PUT
    -0.07
    叨
    -0.06
    REFERRED
    -0.06
    通告
    -0.06
    POSITIVE LOGITS
    birthdate
    0.07
     garments
    0.07
     zone
    0.07
     xb
    0.07
     tracer
    0.07
    ┕
    0.06
    entry
    0.06
     planes
    0.06
     formas
    0.06
    Ос
    0.06
    Act Density 0.004%

    No Known Activations