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

    Neuronpedia

    INDEX
    Explanations

    contractions and informal language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    送料無料
    -0.07
    臣
    -0.07
     hết
    -0.06
    ropolis
    -0.06
    source
    -0.06
    idea
    -0.06
    _closed
    -0.06
     çıkış
    -0.06
    �
    -0.06
     trabal
    -0.06
    POSITIVE LOGITS
    ologi
    0.06
    ture
    0.06
    <th
    0.06
    FINE
    0.06
     اك
    0.06
     downhill
    0.06
    (mask
    0.06
    /footer
    0.06
     ctor
    0.06
     Dec
    0.06
    Act Density 0.047%

    No Known Activations