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

    Neuronpedia

    INDEX
    Explanations

    Latvia-related text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     advise
    -0.07
     över
    -0.07
    arta
    -0.06
    561
    -0.06
     wi
    -0.06
     numa
    -0.06
    429
    -0.06
    deme
    -0.06
     Boat
    -0.06
     ganze
    -0.06
    POSITIVE LOGITS
    aug
    0.12
     Carmen
    0.10
    ug
    0.09
    ugh
    0.07
    ит
    0.07
     Spy
    0.06
     CIT
    0.06
     NotSupportedException
    0.06
     čtyř
    0.06
     itemType
    0.06
    Act Density 0.005%

    No Known Activations