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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     retrieves
    -0.07
    _const
    -0.07
    こんにちは
    -0.07
    ’ın
    -0.06
     McCain
    -0.06
    」と
    -0.06
    送料
    -0.06
    КА
    -0.06
    ");
    -0.06
     pods
    -0.06
    POSITIVE LOGITS
    ム
    0.07
    _backend
    0.07
    ív
    0.06
    462
    0.06
     undergraduate
    0.06
    告诉
    0.06
     life
    0.06
    _times
    0.06
    _cate
    0.06
     Petty
    0.06
    Act Density 0.000%

    No Known Activations