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

    Neuronpedia

    INDEX
    Explanations

    porcelain objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ी
    0.85
     práctica
    0.84
    ిన
    0.80
     pubblic
    0.77
     действу
    0.77
     matemática
    0.76
     circulación
    0.76
    ため
    0.74
    ने
    0.72
    үү
    0.72
    POSITIVE LOGITS
    p
    1.04
     Porcelain
    0.95
    zhou
    0.85
     porcelain
    0.85
    celain
    0.82
    kova
    0.82
     veneers
    0.80
     porcel
    0.79
     shards
    0.78
    veck
    0.75
    Act Density 0.001%

    No Known Activations