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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    รวม
    -0.07
    919
    -0.06
    новаж
    -0.06
     mart
    -0.06
    Nb
    -0.06
     incor
    -0.06
     quo
    -0.06
    инов
    -0.06
    üfus
    -0.06
    าตรฐาน
    -0.06
    POSITIVE LOGITS
    """↵↵
    0.09
    '''↵
    0.08
    '''↵↵
    0.08
     ```↵
    0.07
     '''↵↵
    0.07
    ================================
    0.07
     """↵↵
    0.07
     puede
    0.06
    овах
    0.06
    	↵		↵
    0.06
    Act Density 0.000%

    No Known Activations