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

    Neuronpedia

    INDEX
    Explanations

    pivot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     натураль
    -0.07
     nonsense
    -0.06
    окумент
    -0.06
    .validator
    -0.06
    '|
    -0.06
     colonization
    -0.06
    .Batch
    -0.06
    .words
    -0.06
     відсут
    -0.06
     Т
    -0.06
    POSITIVE LOGITS
    hips
    0.07
    ens
    0.07
     Does
    0.07
    epsilon
    0.06
    ну
    0.06
    択
    0.06
    mn
    0.06
    ,out
    0.06
    br
    0.06
     Reduce
    0.06
    Act Density 0.004%

    No Known Activations