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

    Neuronpedia

    INDEX
    Explanations

    variety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     varieties
    -1.09
    variety
    -1.02
     variety
    -1.00
     variété
    -0.96
     variedades
    -0.94
     completed
    -0.92
     variétés
    -0.91
     étoient
    -0.88
    Variety
    -0.84
     Varieties
    -0.82
    POSITIVE LOGITS
     kasarigan
    0.58
    ponses
    0.48
     rotten
    0.46
     autorytatywna
    0.46
     off
    0.45
     Pas
    0.45
     tắt
    0.45
    ########.
    0.45
    Passcode
    0.45
     thinking
    0.44
    Act Density 0.273%

    No Known Activations