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

    Neuronpedia

    INDEX
    Explanations

    offset text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ồ
    -0.07
     naval
    -0.07
    olicy
    -0.07
     follower
    -0.07
    margin
    -0.07
    :convert
    -0.06
    _PRIV
    -0.06
     �
    -0.06
     Puerto
    -0.06
     rat
    -0.06
    POSITIVE LOGITS
    대
    0.07
                             ↵
    0.07
     göl
    0.06
     Waterloo
    0.06
     transporting
    0.06
     Campbell
    0.06
    ="#
    0.06
     KeyValue
    0.06
    -sign
    0.06
     định
    0.06
    Act Density 0.001%

    No Known Activations