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

    Neuronpedia

    INDEX
    Explanations

    reductive/reducing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     giờ
    -0.07
     bí
    -0.07
    ๊ก
    -0.06
    란
    -0.06
    picture
    -0.06
    bus
    -0.06
    štění
    -0.06
    Border
    -0.06
    nova
    -0.06
    .Observable
    -0.06
    POSITIVE LOGITS
    .Term
    0.07
     dates
    0.07
    (create
    0.06
    _EXTENDED
    0.06
     ราย
    0.06
    ..↵
    0.06
     Has
    0.06
    .Prot
    0.06
    0.06
    ··
    0.06
    Act Density 0.007%

    No Known Activations