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

    Neuronpedia

    INDEX
    Explanations

    apostrophe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     آل
    -0.07
    фа
    -0.07
    ใหญ
    -0.06
    वर
    -0.06
    (...)
    -0.06
     Override
    -0.06
    。しかし
    -0.06
     Wor
    -0.06
     उन
    -0.06
    алу
    -0.06
    POSITIVE LOGITS
     stable
    0.07
    ีม
    0.06
    >\<
    0.06
     File
    0.06
    ]={↵
    0.06
     deceit
    0.06
     crashing
    0.06
     COMMIT
    0.06
    _session
    0.06
    )&
    0.06
    Act Density 0.002%

    No Known Activations