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

    Neuronpedia

    INDEX
    Explanations

    Bank

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    潞
    -0.07
    ").↵↵
    -0.07
    .";
    -0.07
     populist
    -0.06
     szczegółowo
    -0.06
    旅遊
    -0.06
    决心
    -0.06
    僔
    -0.06
    �
    -0.06
     bist
    -0.06
    POSITIVE LOGITS
    fair
    0.08
    probably
    0.07
    very
    0.07
    ategory
    0.07
     annot
    0.07
    formats
    0.07
    иде
    0.07
    よかった
    0.07
    ==============
    0.07
    Replacing
    0.07
    Act Density 0.002%

    No Known Activations