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

    Neuronpedia

    INDEX
    Explanations

    Informal writing fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Save
    -0.07
    анти
    -0.07
    国际
    -0.07
     ending
    -0.07
     Hospitality
    -0.07
     |
    -0.07
    (with
    -0.06
    .allocate
    -0.06
     політи
    -0.06
    _mode
    -0.06
    POSITIVE LOGITS
     �
    0.06
     Sheffield
    0.06
    ]][
    0.06
     Glacier
    0.06
     Plymouth
    0.05
    ORTH
    0.05
     rented
    0.05
    rání
    0.05
    ]+=
    0.05
     منطقة
    0.05
    Act Density 0.785%

    No Known Activations