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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.07
    cpy
    -0.07
    月下
    -0.07
    起飞
    -0.06
     quad
    -0.06
    צת
    -0.06
    .SetValue
    -0.06
    .solve
    -0.06
    զ
    -0.06
    一声
    -0.06
    POSITIVE LOGITS
    �
    0.08
    -art
    0.08
    _rt
    0.07
     ARC
    0.07
    ahrungen
    0.07
     pubs
    0.07
     alterations
    0.07
    源自
    0.06
    (!
    0.06
     Builder
    0.06
    Act Density 0.114%

    No Known Activations