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

    Neuronpedia

    INDEX
    Explanations

    program context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vehículo
    0.63
     là
    0.57
     vértice
    0.55
     veículo
    0.53
     vehículos
    0.52
     diámetro
    0.51
     dará
    0.48
     jugó
    0.48
     araç
    0.48
     gráfico
    0.47
    POSITIVE LOGITS
    nent
    0.47
    ात्
    0.43
    regular
    0.41
     정신
    0.41
    self
    0.41
    nen
    0.41
    protected
    0.39
    s
    0.39
     Newsletter
    0.38
    act
    0.38
    Act Density 0.000%

    No Known Activations