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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kte
    -0.07
    什么
    -0.07
     Крім
    -0.06
     incompatible
    -0.06
    ...",↵
    -0.06
     způsobem
    -0.06
     hmm
    -0.06
    INCLUDED
    -0.06
    Occurrences
    -0.06
     xen
    -0.06
    POSITIVE LOGITS
     Beau
    0.07
     Wilderness
    0.06
    reply
    0.06
     चल
    0.06
     Treasury
    0.06
    ittle
    0.06
     ninguna
    0.06
     tutar
    0.06
     Merc
    0.06
     ResourceManager
    0.06
    Act Density 0.000%

    No Known Activations