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

    Neuronpedia

    INDEX
    Explanations

    tolerance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arsimp
    -0.07
    gmail
    -0.07
     цієї
    -0.06
    едж
    -0.06
     tallest
    -0.06
    .after
    -0.06
    �a
    -0.06
     unspecified
    -0.06
    тися
    -0.06
    ::::::::
    -0.06
    POSITIVE LOGITS
     Vermont
    0.07
    .energy
    0.07
     indicator
    0.07
     Australians
    0.06
    社区
    0.06
     aggregate
    0.06
     deferred
    0.06
     hom
    0.06
     armored
    0.06
     Japanese
    0.06
    Act Density 0.003%

    No Known Activations