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

    Neuronpedia

    INDEX
    Explanations

    Separating information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    positions
    -0.06
     functools
    -0.06
    606
    -0.06
    _COLLECTION
    -0.06
    HIGH
    -0.06
     Tops
    -0.06
    ₁
    -0.06
    tracker
    -0.06
    :')
    -0.06
    _Checked
    -0.06
    POSITIVE LOGITS
     وفق
    0.07
     Verd
    0.06
     zákona
    0.06
     измен
    0.06
     con
    0.06
     domestically
    0.06
    (inner
    0.06
     SG
    0.06
    Supply
    0.06
     parms
    0.06
    Act Density 0.002%

    No Known Activations