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

    Neuronpedia

    INDEX
    Explanations

    say "by" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    очные
    -0.07
     تصو
    -0.06
    ]))↵↵
    -0.06
     "")↵↵
    -0.06
    *)↵↵
    -0.06
    """
↵
↵
    -0.06
     figured
    -0.06
    手
    -0.06
    )])↵↵
    -0.06
    ）の
    -0.06
    POSITIVE LOGITS
     прит
    0.07
    /fs
    0.07
    _lin
    0.07
    .os
    0.06
     Re
    0.06
    CMS
    0.06
    contain
    0.06
    _Free
    0.06
    temp
    0.06
    Lens
    0.06
    Act Density 1.979%

    No Known Activations