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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ن
    -0.06
    žel
    -0.06
    리가
    -0.06
     Insider
    -0.06
    ród
    -0.06
    発
    -0.06
     Din
    -0.06
    黑
    -0.06
     oasis
    -0.06
    ستگی
    -0.06
    POSITIVE LOGITS
    .getIndex
    0.06
    626
    0.06
     airl
    0.06
    ample
    0.06
    Inline
    0.06
     побед
    0.06
    Bet
    0.06
    -top
    0.06
    (pool
    0.06
     Inline
    0.06
    Act Density 0.023%

    No Known Activations