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

    Neuronpedia

    INDEX
    Explanations

    disguises and transformations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    леб
    -0.08
     Universe
    -0.08
     ahol
    -0.08
     nutrients
    -0.07
     objed
    -0.07
    يط
    -0.07
    .Elements
    -0.07
    noopener
    -0.07
     nourish
    -0.07
     landen
    -0.07
    POSITIVE LOGITS
     disguis
    0.12
     disguise
    0.11
     अभिनय
    0.10
     anonymity
    0.10
     disguised
    0.10
     gait
    0.09
     masquer
    0.09
     accent
    0.09
     costume
    0.09
     അഭിനയ
    0.09
    Act Density 0.035%

    No Known Activations