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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Automotive
    -0.07
    (save
    -0.07
    heads
    -0.06
    حم
    -0.06
     fan
    -0.06
     shifted
    -0.06
    .getColor
    -0.06
     Sold
    -0.06
    (stop
    -0.06
     swallow
    -0.06
    POSITIVE LOGITS
     exc
    0.07
     Rep
    0.07
     ej
    0.06
    abetes
    0.06
    ंबर
    0.06
     několik
    0.06
     incidental
    0.06
    ClassName
    0.06
    จำก
    0.06
     एम
    0.06
    Act Density 0.000%

    No Known Activations